© 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. 3-RESID-POST-AA
    11. 123107
    Prev
    Next
    INDEX
    Explanations

    version

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ，可
    -0.08
    ()>
    -0.07
    `"]↵
    -0.07
    },'
    -0.06
    Planning
    -0.06
    τερ
    -0.06
    nothing
    -0.06
     своїм
    -0.06
     ⇒
    -0.06
     ROC
    -0.06
    POSITIVE LOGITS
     underside
    0.15
    /version
    0.09
    -BEGIN
    0.07
    (strict
    0.07
    (distance
    0.07
    063
    0.06
     Dün
    0.06
     CONF
    0.06
    avy
    0.06
    ample
    0.06
    Activations Density 0.003%

    No Known Activations