© 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. 66171
    Prev
    Next
    INDEX
    Explanations

    ordinals

    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
    232
    -0.08
     locked
    -0.07
    adastrar
    -0.07
     stunned
    -0.07
     сент
    -0.07
     Herc
    -0.06
     lasting
    -0.06
     Jack
    -0.06
    .mb
    -0.06
    .MiddleLeft
    -0.06
    POSITIVE LOGITS
     lombok
    0.07
    .xx
    0.06
     مط
    0.06
    ipo
    0.06
     arithmetic
    0.06
    --
↵
    0.06
     منها
    0.06
    maf
    0.06
    cko
    0.05
     Mathematical
    0.05
    Activations Density 0.008%

    No Known Activations