Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 5034
    Prev
    Next
    INDEX
    Explanations

    development

    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
    ')));↵↵
    -0.07
     tgt
    -0.07
    _P
    -0.07
    ,r
    -0.07
    ологіч
    -0.06
    увалися
    -0.06
     θέση
    -0.06
     Lion
    -0.06
    '})↵↵
    -0.06
     Edison
    -0.06
    POSITIVE LOGITS
     أل
    0.08
    addle
    0.06
     implode
    0.06
    ポート
    0.06
     MPL
    0.06
    _terminal
    0.06
     fraught
    0.06
    productive
    0.06
    destroy
    0.06
     개발
    0.06
    Activations Density 0.022%

    No Known Activations