© 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. 7-RESID-POST-AA
    11. 19313
    Prev
    Next
    INDEX
    Explanations

    Enclosing, encircling

    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
     [#
    -0.07
     dropping
    -0.06
    .**************↵
    -0.06
    _FILTER
    -0.06
    .Win
    -0.06
     drop
    -0.06
    _Right
    -0.06
    。↵↵
    -0.06
     irresistible
    -0.06
    [K
    -0.06
    POSITIVE LOGITS
    aha
    0.07
     yö
    0.07
     vypl
    0.07
    ảo
    0.07
     spheres
    0.06
    lauf
    0.06
     �
    0.06
    \Backend
    0.06
     OUTER
    0.06
     Loop
    0.06
    Activations Density 0.182%

    No Known Activations