© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90904
    Prev
    Next
    INDEX
    Explanations

    Coverage

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect numeric literals (especially version, size, or coverage numbers) in structured file‐metadata entries.

    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
     Tib
    -0.07
     Hannah
    -0.07
    idia
    -0.06
    urence
    -0.06
     diam
    -0.06
     white
    -0.06
    clock
    -0.06
     cardiac
    -0.06
     Frances
    -0.06
     Tf
    -0.06
    POSITIVE LOGITS
    _metric
    0.07
    TextField
    0.07
     часто
    0.07
     duel
    0.06
     schema
    0.06
    情報
    0.06
     ",");↵
    0.06
     канди
    0.06
    )value
    0.06
     descon
    0.06
    Activations Density 0.000%

    No Known Activations