© 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. 6561
    Prev
    Next
    INDEX
    Explanations

    data computation

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literal tokens—especially decimal numbers—within the tabular data.

    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
     #####
    -0.08
    لت
    -0.07
    (filtered
    -0.07
    _NET
    -0.07
    (lr
    -0.06
    roc
    -0.06
    чого
    -0.06
     полі
    -0.06
    Forest
    -0.06
    कर
    -0.06
    POSITIVE LOGITS
    coe
    0.06
     esta
    0.06
     replicas
    0.06
     yapacak
    0.06
     RM
    0.06
     Armenian
    0.06
     odv
    0.06
     conclude
    0.06
     fond
    0.06
    ooting
    0.06
    Activations Density 0.041%

    No Known Activations