© 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. 94158
    Prev
    Next
    INDEX
    Explanations

    Code/identifiers in text

    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
    a
    -0.07
     Clippers
    -0.07
     arou
    -0.07
    As
    -0.07
    (values
    -0.07
    _COMPAT
    -0.06
    .coords
    -0.06
     Tactics
    -0.06
    idelity
    -0.06
    탈
    -0.06
    POSITIVE LOGITS
     okolí
    0.07
     colormap
    0.07
    ा↵
    0.06
    .XtraEditors
    0.06
    endereco
    0.06
    _png
    0.06
     inexperienced
    0.05
     производ
    0.05
    _crossentropy
    0.05
    (clazz
    0.05
    Activations Density 2.226%

    No Known Activations