© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109074
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    np_max-act · gemini-2.0-flash

    regex patterns that match specific strings while excluding unwanted segments, such as those within quotation marks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects regex metacharacters and constructs—specifically the opening of character classes ([…]) and grouping patterns (parentheses, non-capturing groups, escapes, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -bed
    -0.07
    MSG
    -0.07
    죠
    -0.07
    BaseUrl
    -0.06
    ifetime
    -0.06
     sensed
    -0.06
    یان
    -0.06
    上了
    -0.06
    AILY
    -0.06
     اینکه
    -0.06
    POSITIVE LOGITS
     depressive
    0.08
     поскольку
    0.06
    -plugin
    0.06
    izzazione
    0.06
     Bhar
    0.06
    ्ष
    0.06
    Він
    0.06
    _maker
    0.06
     司
    0.06
    ующих
    0.06
    Activations Density 0.027%

    No Known Activations