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. 18737
    Prev
    Next
    INDEX
    Explanations

    candle

    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
    _nv
    -0.08
    ουργ
    -0.07
    부분
    -0.06
     znal
    -0.06
    历史
    -0.06
    ्रण
    -0.06
    	friend
    -0.06
    ’int
    -0.06
    ursors
    -0.06
    uti
    -0.06
    POSITIVE LOGITS
     FREE
    0.07
     '$
    0.06
     Mike
    0.06
     tavern
    0.06
    秒
    0.06
    Mike
    0.06
    caster
    0.06
    Die
    0.06
    gb
    0.06
    deen
    0.06
    Activations Density 0.003%

    No Known Activations