© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29938
    Prev
    Next
    INDEX
    Explanations

    omatic

    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
     fire
    -0.07
    REF
    -0.07
    dur
    -0.07
     colors
    -0.06
    िल
    -0.06
    Spin
    -0.06
     FIRE
    -0.06
     herbal
    -0.06
     succeeding
    -0.06
     herbs
    -0.06
    POSITIVE LOGITS
    -employed
    0.07
    (TM
    0.07
    omatic
    0.07
     маз
    0.06
     nemoc
    0.06
    рег
    0.06
     unaffected
    0.06
    emble
    0.06
    _MSK
    0.06
    rame
    0.06
    Activations Density 0.003%

    No Known Activations