© 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. 90886
    Prev
    Next
    INDEX
    Explanations

    also

    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
    /original
    -0.07
     />,↵
    -0.07
    ,)
    -0.06
    (IB
    -0.06
     '{}
    -0.06
    )++;↵
    -0.06
     ~(
    -0.06
    (players
    -0.06
     int
    -0.06
    طع
    -0.06
    POSITIVE LOGITS
     Award
    0.07
     collaborating
    0.07
    쟁
    0.07
     also
    0.07
     lifes
    0.07
    theon
    0.07
     Lands
    0.07
     murderous
    0.07
    translation
    0.07
     Cart
    0.06
    Activations Density 0.043%

    No Known Activations