© 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. 11-RESID-POST-AA
    11. 25925
    Prev
    Next
    INDEX
    Explanations

    Companies

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     takdir
    -0.07
     SMS
    -0.07
    ĩnh
    -0.06
    Average
    -0.06
     rate
    -0.06
     backgrounds
    -0.06
    得到
    -0.06
     tisíc
    -0.06
     radi
    -0.06
     pounding
    -0.06
    POSITIVE LOGITS
    _EDEFAULT
    0.07
    .assertNot
    0.07
     makeStyles
    0.06
    バス
    0.06
    .TestCheck
    0.06
    scrollView
    0.06
     ButterKnife
    0.06
    makes
    0.06
    woord
    0.06
     ----------------------------------------------------------------------------------------------------------------
    0.06
    Activations Density 0.103%

    No Known Activations