© 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. 887
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find numeric literals within code.

    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
    yper
    -0.07
    neutral
    -0.07
    adows
    -0.06
    нут
    -0.06
    acking
    -0.06
    once
    -0.06
     Kiş
    -0.06
     vide
    -0.06
    clusion
    -0.06
    aggi
    -0.06
    POSITIVE LOGITS
    _executor
    0.06
    _author
    0.06
    0.06
     sku
    0.06
    (crate
    0.06
     Db
    0.06
     august
    0.06
    'I
    0.06
    ■■
    0.06
    诺
    0.06
    Activations Density 0.063%

    No Known Activations