© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41444
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron is triggered by digit tokens (e.g. “1”, “2”, etc.) appearing in navigation/menu identifiers or page‐index contexts.

    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
    KI
    -0.07
    gium
    -0.06
    .xr
    -0.06
    }/>
    -0.06
    _word
    -0.06
    Ğİ
    -0.06
    _CUSTOMER
    -0.06
    toy
    -0.06
    ична
    -0.06
    ACKET
    -0.06
    POSITIVE LOGITS
     cran
    0.07
     गर
    0.06
     shimmer
    0.06
    ी
    0.06
     студ
    0.06
     brake
    0.06
    weathermap
    0.06
    播放
    0.06
     Stir
    0.06
     náklad
    0.06
    Activations Density 0.002%

    No Known Activations