© 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. 113255
    Prev
    Next
    INDEX
    Explanations

    pacifier

    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
    439
    -0.06
    770
    -0.06
     tep
    -0.06
    iniz
    -0.06
     bức
    -0.06
    حم
    -0.06
    upgrade
    -0.06
    _pic
    -0.06
    aylight
    -0.06
    ounced
    -0.06
    POSITIVE LOGITS
    Tra
    0.06
     cling
    0.06
    <context
    0.06
    Susan
    0.06
     augment
    0.06
     contextual
    0.06
    ANGER
    0.06
     ит
    0.06
     ủy
    0.06
    nation
    0.06
    Activations Density 0.002%

    No Known Activations