© 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. 19-RESID-POST-AA
    11. 35200
    Prev
    Next
    INDEX
    Explanations

    Forbidden

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     людям
    -0.07
     언제
    -0.07
     Lưu
    -0.07
     navigationController
    -0.07
     nuôi
    -0.06
     Souls
    -0.06
     качестве
    -0.06
     Ultimate
    -0.06
    никами
    -0.06
     žena
    -0.06
    POSITIVE LOGITS
    قات
    0.07
    函
    0.07
     prohibition
    0.07
    fon
    0.07
     prohibit
    0.07
     barriers
    0.07
     forb
    0.07
    GG
    0.07
    .prepend
    0.06
     fif
    0.06
    Activations Density 0.005%

    No Known Activations