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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55828
    Prev
    Next
    INDEX
    Explanations

    Common words in long sentences

    np_max-act · gemini-2.0-flash

    The neuron responds to punctuation marks and numeric tokens (e.g. commas, periods, digits), effectively spotting sentence boundaries and numerical/date elements.

    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
    endment
    -0.07
    psilon
    -0.07
    arLayout
    -0.07
    _negative
    -0.07
     стоит
    -0.06
     painfully
    -0.06
    rin
    -0.06
     máximo
    -0.06
    тов
    -0.06
    誤
    -0.06
    POSITIVE LOGITS
     symb
    0.07
    deep
    0.07
     Already
    0.06
     topLevel
    0.06
     bundled
    0.06
     Ülke
    0.06
     bool
    0.06
     своїх
    0.06
    uba
    0.06
     Olivier
    0.06
    Activations Density 0.123%

    No Known Activations