© 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. 9572
    Prev
    Next
    INDEX
    Explanations

    vote

    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
    628
    -0.07
    StringRef
    -0.07
     briefed
    -0.07
     rows
    -0.07
     release
    -0.07
     vých
    -0.07
     Certainly
    -0.06
    vinc
    -0.06
     fastest
    -0.06
     aras
    -0.06
    POSITIVE LOGITS
    英語
    0.06
     defStyleAttr
    0.06
    わり
    0.06
     Pirates
    0.06
     voting
    0.06
    ién
    0.06
    ')}↵
    0.06
     Communities
    0.05
    мом
    0.05
    (Base
    0.05
    Activations Density 0.015%

    No Known Activations