© 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. 109475
    Prev
    Next
    INDEX
    Explanations

    running

    np_max-act · gemini-2.0-flash

    The neuron signals the presence of running-back–related terminology (mentions of running back or rushing roles) in football coverage.

    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
     convent
    -0.07
     ух
    -0.06
     connectionString
    -0.06
    �
    -0.06
    .Theme
    -0.06
     себ
    -0.06
    ADM
    -0.06
     推
    -0.06
    john
    -0.06
    Ef
    -0.06
    POSITIVE LOGITS
    .Cryptography
    0.06
     RNG
    0.06
    與
    0.06
    …"↵↵
    0.06
     setDate
    0.06
     modifications
    0.06
    етель
    0.06
    isnan
    0.06
    .tag
    0.06
    recision
    0.06
    Activations Density 0.011%

    No Known Activations