© 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. 15-RESID-POST-AA
    11. 40877
    Prev
    Next
    INDEX
    Explanations

    symmetry

    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
     Gol
    -0.07
    (old
    -0.07
     cul
    -0.07
    Fetching
    -0.07
    .Brand
    -0.07
    .Flags
    -0.07
    did
    -0.06
     AOL
    -0.06
     realiza
    -0.06
     úrov
    -0.06
    POSITIVE LOGITS
     symmetry
    0.09
     sym
    0.09
     Sym
    0.08
    머
    0.08
     turnovers
    0.07
     Armstrong
    0.07
     same
    0.07
    _armor
    0.07
     sway
    0.07
     simultaneously
    0.06
    Activations Density 0.008%

    No Known Activations