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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    6. 125895
    Prev
    Next
    INDEX
    Explanations

    zip codes

    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
    (selection
    -0.08
    adox
    -0.07
    Ξ
    -0.06
    !=
    -0.06
    IMATION
    -0.06
     lavoro
    -0.06
    ME
    -0.06
    me
    -0.06
     Marshall
    -0.06
    chemes
    -0.06
    POSITIVE LOGITS
    _decay
    0.06
     MouseEvent
    0.06
    (row
    0.06
     чуд
    0.06
     gluten
    0.06
    тє
    0.06
     jButton
    0.06
     insult
    0.06
    しました
    0.06
     Keyword
    0.06
    Activations Density 0.019%

    No Known Activations