© 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. 3-RESID-POST-AA
    6. 123201
    Prev
    Next
    INDEX
    Explanations

    level

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _cost
    -0.08
    user
    -0.07
    ichten
    -0.07
     hedge
    -0.06
     fuse
    -0.06
    poss
    -0.06
     lose
    -0.06
    Ignore
    -0.06
    _b
    -0.06
     زمین
    -0.06
    POSITIVE LOGITS
     levels
    0.11
     Levels
    0.10
     level
    0.08
    Levels
    0.08
     �
    0.07
     استخدام
    0.07
     contentValues
    0.07
    인증
    0.07
     Глав
    0.07
     laz
    0.07
    Activations Density 0.019%

    No Known Activations