© 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 (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 80406
    Prev
    Next
    INDEX
    Explanations

    learning to stop something

    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
    .apple
    -0.07
     automation
    -0.06
    fish
    -0.06
     длитель
    -0.06
     exposure
    -0.06
     tobacco
    -0.06
     elite
    -0.06
     여자
    -0.06
    кових
    -0.06
    	ref
    -0.06
    POSITIVE LOGITS
    /gcc
    0.07
    ése
    0.06
     теперь
    0.06
     seper
    0.06
    .rotate
    0.06
    |M
    0.06
    _switch
    0.06
     πρά
    0.06
    .ModelSerializer
    0.06
    OfSize
    0.06
    Activations Density 0.062%

    No Known Activations