© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 115525
    Prev
    Next
    INDEX
    Explanations

    Personal opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    special
    -0.07
     sidewalk
    -0.07
    Professional
    -0.07
     stmt
    -0.07
    _Result
    -0.07
     professional
    -0.07
    .number
    -0.06
     special
    -0.06
    bindParam
    -0.06
     exploded
    -0.06
    POSITIVE LOGITS
    �
    0.07
     Investments
    0.07
     rated
    0.06
    [at
    0.06
    =!
    0.06
     ΠΑΝ
    0.06
    )...
    0.06
     Due
    0.06
    AndGet
    0.06
     sabah
    0.06
    Activations Density 0.067%

    No Known Activations