© 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. 18212
    Prev
    Next
    INDEX
    Explanations

    decode

    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
    _HIT
    -0.07
     постав
    -0.07
    _frequency
    -0.07
     groot
    -0.07
     produto
    -0.07
     hwnd
    -0.07
     font
    -0.07
     Ruth
    -0.07
    istributed
    -0.07
     Pap
    -0.07
    POSITIVE LOGITS
    Decoder
    0.10
     decoding
    0.09
    Decode
    0.08
     dec
    0.07
    DE
    0.07
    .decrypt
    0.07
    decoded
    0.07
     redeem
    0.07
    Dec
    0.07
     redeemed
    0.07
    Activations Density 0.013%

    No Known Activations