© 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. 7-RESID-POST-AA
    6. 24993
    Prev
    Next
    INDEX
    Explanations

    )

    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
    ocene
    -0.08
     dog
    -0.07
    .loc
    -0.07
    .Ad
    -0.07
    _ad
    -0.06
     часов
    -0.06
    urniture
    -0.06
    _the
    -0.06
    erman
    -0.06
     crashed
    -0.06
    POSITIVE LOGITS
     nieu
    0.07
     чолов
    0.07
    乘
    0.07
     preserved
    0.06
    ія
    0.06
    ios
    0.06
    (flow
    0.06
     McM
    0.06
     πρώ
    0.06
    افظ
    0.06
    Activations Density 0.039%

    No Known Activations