© 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. 30496
    Prev
    Next
    INDEX
    Explanations

    code commands/syntax

    np_max-act · gemini-2.0-flash

    This neuron fires on uppercase enum‐style type identifiers in code (e.g. references like ClassNames.ACTIVITY or TypeName.VOID).

    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
    Monitor
    -0.07
    ámara
    -0.07
     almonds
    -0.07
    urus
    -0.06
    라마
    -0.06
     fox
    -0.06
     ques
    -0.06
     claws
    -0.06
     Vaults
    -0.06
     Readers
    -0.06
    POSITIVE LOGITS
    (tolua
    0.06
    子の
    0.06
    .randrange
    0.06
    (APP
    0.05
    .parseDouble
    0.05
    PRIMARY
    0.05
    $get
    0.05
    プリ
    0.05
    �
    0.05
    _G
    0.05
    Activations Density 0.065%

    No Known Activations