© 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. 90580
    Prev
    Next
    INDEX
    Explanations

    din

    np_max-act · gemini-2.0-flash

    This neuron lightly activates on uncommon or low‐frequency subword tokens (i.e. rare character sequences regardless of part of speech).

    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
     YouTube
    -0.07
     Invocation
    -0.06
     posed
    -0.06
    /features
    -0.06
     implementations
    -0.06
     통합
    -0.06
     Wat
    -0.06
     باب
    -0.06
     tribe
    -0.06
    یط
    -0.06
    POSITIVE LOGITS
     IOError
    0.07
    など
    0.07
    .ReadInt
    0.07
    DateFormat
    0.07
    _STATE
    0.06
    _tf
    0.06
    тах
    0.06
    Moving
    0.06
    ")->
    0.06
    LL
    0.06
    Activations Density 0.000%

    No Known Activations