© 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. 105296
    Prev
    Next
    INDEX
    Explanations

    receptor

    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
     Wednesday
    -0.08
     trading
    -0.08
     Tuesday
    -0.07
     Trading
    -0.07
    在线观看
    -0.07
     Daily
    -0.07
    256
    -0.07
    _slice
    -0.07
    ize
    -0.07
    57
    -0.06
    POSITIVE LOGITS
     receptor
    0.11
     receptors
    0.09
    ceptor
    0.08
     recept
    0.07
    ór
    0.07
     kapı
    0.07
    ometr
    0.07
     recep
    0.07
     Robert
    0.07
     relación
    0.07
    Activations Density 0.009%

    No Known Activations