© 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. 80504
    Prev
    Next
    INDEX
    Explanations

    extends

    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
     Cou
    -0.06
    ameleon
    -0.06
    励
    -0.06
    (np
    -0.06
     penalty
    -0.06
    XS
    -0.06
     KUR
    -0.06
    obi
    -0.06
    (mask
    -0.06
    ename
    -0.06
    POSITIVE LOGITS
     Registers
    0.07
    .ContentType
    0.07
    untime
    0.07
     coping
    0.07
     inserted
    0.06
     generations
    0.06
     severed
    0.06
     RETURN
    0.06
     extends
    0.06
     Outer
    0.06
    Activations Density 0.002%

    No Known Activations