© 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. 15-RESID-POST-AA
    11. 102115
    Prev
    Next
    INDEX
    Explanations

    challenge

    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
     эк
    -0.07
     spéc
    -0.06
    .act
    -0.06
    .chain
    -0.06
     clot
    -0.06
     rake
    -0.06
    _al
    -0.06
    alternative
    -0.06
     truyền
    -0.06
    second
    -0.06
    POSITIVE LOGITS
    ians
    0.07
     heals
    0.07
    (:,:,
    0.07
    olla
    0.07
    _kel
    0.07
     انسانی
    0.06
            ↵        ↵        ↵
    0.06
     anal
    0.06
     opposes
    0.06
     GV
    0.06
    Activations Density 0.134%

    No Known Activations