© 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. 90846
    Prev
    Next
    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens, specifically decimal numbers with fractional parts (e.g., “0.70703125,” “1.1943359375,” etc.).

    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
    obierno
    -0.06
    ौद
    -0.06
    jenis
    -0.06
    طفال
    -0.06
     другого
    -0.06
    ratulations
    -0.06
    ManyToOne
    -0.05
    Descripcion
    -0.05
     Iranian
    -0.05
    orgetown
    -0.05
    POSITIVE LOGITS
    ,\↵
    0.07
    ha
    0.07
     Nacional
    0.07
     Recon
    0.07
    evaluate
    0.07
     falsely
    0.06
    ivas
    0.06
     �
    0.06
    \e
    0.06
    **(
    0.06
    Activations Density 0.019%

    No Known Activations