© 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 EvalsExportsAPI 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. 38319
    Prev
    Next
    INDEX
    Explanations

    imports

    np_max-act · gemini-2.0-flash

    This neuron activates on programming‐style identifiers, especially library or API names and their associated functions or types.

    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
    —for
    -0.08
     �
    -0.08
    ㅠ
    -0.07
     було
    -0.07
    .TEXTURE
    -0.07
    确定
    -0.07
    िए
    -0.07
     ALOG
    -0.07
    tgt
    -0.07
    Keep
    -0.06
    POSITIVE LOGITS
    ดร
    0.08
     staggering
    0.06
     기본
    0.06
     ella
    0.06
     gradual
    0.06
     Martin
    0.06
     cargar
    0.05
     conventional
    0.05
    /m
    0.05
     Command
    0.05
    Activations Density 0.021%

    No Known Activations