© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 99615
    Prev
    Next
    INDEX
    Explanations

    correlate

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spree
    -0.07
     ¦
    -0.06
     Interval
    -0.06
    cour
    -0.06
     IDX
    -0.06
     DWC
    -0.06
    peated
    -0.06
    upid
    -0.06
     Pitt
    -0.06
     id
    -0.06
    POSITIVE LOGITS
    lanmış
    0.07
     XPath
    0.06
     brewers
    0.06
     getField
    0.06
    هدف
    0.06
    (Status
    0.06
     rtrim
    0.06
    _condition
    0.06
     Morales
    0.06
    AUSE
    0.06
    Activations Density 0.020%

    No Known Activations