Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126905
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive and doesn’t detect any particular pattern.

    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
     Gibraltar
    -0.08
     boil
    -0.06
    XXX
    -0.06
     şekl
    -0.06
    paněl
    -0.06
     frat
    -0.06
     timespec
    -0.06
    ammed
    -0.06
    unbind
    -0.06
     Ad
    -0.06
    POSITIVE LOGITS
    alias
    0.07
     outstanding
    0.07
    _RESOURCES
    0.06
    velocity
    0.06
     correct
    0.06
    simple
    0.06
    riage
    0.06
    keiten
    0.06
    >"↵
    0.06
     prag
    0.06
    Activations Density 0.047%

    No Known Activations