© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44308
    Prev
    Next
    INDEX
    Explanations

    science

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on technical, scientific, or experimental terms—i.e. words that describe apparatus, methods, materials, or phenomena in scientific reasoning or experimentation.

    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
    _NOTIFY
    -0.07
    Baseline
    -0.07
    rho
    -0.07
    discard
    -0.07
    .accept
    -0.06
    .D
    -0.06
    nap
    -0.06
    .CreateCommand
    -0.06
    iping
    -0.06
    usuario
    -0.06
    POSITIVE LOGITS
     vol
    0.06
    
    0.06
    ая
    0.06
     malaria
    0.06
     hairstyles
    0.06
     فتح
    0.06
     tied
    0.06
     //↵↵
    0.06
    ~↵
    0.06
    :";↵
    0.06
    Activations Density 0.023%

    No Known Activations