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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 85789
    Prev
    Next
    INDEX
    Explanations

    must

    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
     releasing
    -0.07
     Asia
    -0.06
     +'
    -0.06
     filetype
    -0.06
     spirituality
    -0.06
    _timing
    -0.06
     ‏
    -0.06
     людина
    -0.06
     weekdays
    -0.06
    fieldname
    -0.06
    POSITIVE LOGITS
    EI
    0.08
    oj
    0.07
    ej
    0.07
    687
    0.06
    ≥
    0.06
     sina
    0.06
    す
    0.06
    dığ
    0.06
    ope
    0.06
    Shock
    0.06
    Activations Density 0.033%

    No Known Activations