© 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. 11-RESID-POST-AA
    11. 123922
    Prev
    Next
    INDEX
    Explanations

    print

    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
     escalation
    -0.07
     goal
    -0.06
    .isDefined
    -0.06
     undefined
    -0.06
     Denied
    -0.06
    éry
    -0.06
    ССР
    -0.06
     Disabled
    -0.06
    imeters
    -0.06
     settlement
    -0.06
    POSITIVE LOGITS
     TEMP
    0.07
    ,i
    0.07
    (i
    0.07
    派
    0.07
    /*.
    0.06
     امر
    0.06
    738
    0.06
    รอง
    0.06
    TEMP
    0.06
     caravan
    0.06
    Activations Density 0.015%

    No Known Activations