Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 112587
    Prev
    Next
    INDEX
    Explanations

    medical treatment

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.08
     ваш
    -0.07
     pp
    -0.06
    793
    -0.06
     genders
    -0.06
    Reviewed
    -0.06
    ียบ
    -0.06
    txt
    -0.06
    _HERSHEY
    -0.06
     sustain
    -0.06
    POSITIVE LOGITS
     celebrates
    0.06
    aepernick
    0.06
     slipped
    0.06
    Attempts
    0.06
     loaf
    0.06
    .updated
    0.06
     RULE
    0.06
    Pat
    0.06
     ル
    0.06
    _WEIGHT
    0.06
    Activations Density 0.111%

    No Known Activations