© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 60056
    Prev
    Next
    INDEX
    Explanations

    -paced

    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
    روع
    -0.07
    지
    -0.06
    TRAIN
    -0.06
    от
    -0.06
    ,↵↵↵
    -0.06
    Kit
    -0.06
     terminals
    -0.06
    ені
    -0.06
    terní
    -0.06
    З
    -0.06
    POSITIVE LOGITS
    -paced
    0.09
     paced
    0.07
     paddingLeft
    0.07
    ，请
    0.07
    maxLength
    0.07
    -parser
    0.07
    $('
    0.07
    operand
    0.06
    (prev
    0.06
     navigate
    0.06
    Activations Density 0.004%

    No Known Activations