© 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. 23-RESID-POST-AA
    6. 105129
    Prev
    Next
    INDEX
    Explanations

    legal codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bundesliga
    -0.06
    uste
    -0.06
     Sevilla
    -0.06
    /commons
    -0.06
    Middle
    -0.06
    umped
    -0.06
     ↵↵
    -0.06
    erve
    -0.06
    атки
    -0.06
    LES
    -0.06
    POSITIVE LOGITS
     पक
    0.07
     می
    0.06
     favor
    0.06
     pity
    0.06
     launder
    0.06
     nod
    0.06
    超过
    0.06
    参与
    0.06
     sour
    0.06
    Δ
    0.06
    Activations Density 0.003%

    No Known Activations