© 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. 15-RESID-POST-AA
    11. 29906
    Prev
    Next
    INDEX
    Explanations

    historical texts

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ratio
    -0.06
     hauling
    -0.06
    _clr
    -0.06
    Includes
    -0.06
    停止
    -0.06
     هش
    -0.06
    تى
    -0.06
    isku
    -0.06
     Terminal
    -0.06
     Patton
    -0.06
    POSITIVE LOGITS
    lub
    0.07
    .debian
    0.07
    _component
    0.07
     addslashes
    0.07
     мер
    0.06
    levator
    0.06
    source
    0.06
     hedef
    0.06
    nz
    0.06
     ancient
    0.06
    Activations Density 0.044%

    No Known Activations