© 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. 130080
    Prev
    Next
    INDEX
    Explanations

    f

    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
     impass
    -0.06
     distorted
    -0.06
     buna
    -0.06
     kleine
    -0.06
    办
    -0.06
     salida
    -0.06
     має
    -0.06
     будто
    -0.06
     hawk
    -0.06
    leanup
    -0.06
    POSITIVE LOGITS
    -negative
    0.06
     handicap
    0.06
    G
    0.06
    acic
    0.06
    aptic
    0.06
     gf
    0.06
    특별
    0.06
    fy
    0.06
    літ
    0.06
    자
    0.06
    Activations Density 0.002%

    No Known Activations