© 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. 19-RESID-POST-AA
    11. 73180
    Prev
    Next
    INDEX
    Explanations

    Technical processes/analysis

    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
     По
    -0.07
     Coming
    -0.07
    .tests
    -0.06
    .assert
    -0.06
     cheque
    -0.06
    .messages
    -0.06
     baise
    -0.06
     Century
    -0.06
     rail
    -0.06
    ñana
    -0.06
    POSITIVE LOGITS
    (groups
    0.06
     Socorro
    0.06
     zah
    0.06
    운동
    0.06
     essen
    0.06
    -wide
    0.06
     Okay
    0.06
     icy
    0.05
    amilia
    0.05
     永
    0.05
    Activations Density 0.400%

    No Known Activations