© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58826
    Prev
    Next
    INDEX
    Explanations

    higher

    np_max-act · gemini-2.0-flash

    This neuron fires on individual bullet‐style explanation points—that is, short descriptive list items (e.g. lines beginning with a dash in an explanatory list).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     playable
    -0.08
    Hint
    -0.06
     winds
    -0.06
    िं
    -0.06
    .When
    -0.06
     abortions
    -0.06
    posting
    -0.06
     putt
    -0.06
     consciousness
    -0.06
    ونت
    -0.06
    POSITIVE LOGITS
     Πολι
    0.07
     QTimer
    0.07
     Syracuse
    0.07
     Approximately
    0.07
    ****↵
    0.07
    //[
    0.06
    /Table
    0.06
     Belediyesi
    0.06
    ários
    0.06
    ης
    0.06
    Activations Density 0.186%

    No Known Activations