© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56011
    Prev
    Next
    INDEX
    Explanations

    Deleting/removing

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens representing non-integer (decimal) activations—i.e. floating-point numbers in the text.

    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
    anian
    -0.06
     insect
    -0.06
     الط
    -0.06
     feminist
    -0.06
     prophets
    -0.06
    oran
    -0.06
    -spin
    -0.06
    Assembly
    -0.06
    ulings
    -0.06
    iples
    -0.06
    POSITIVE LOGITS
     coal
    0.08
     जब
    0.07
     görüntü
    0.07
    data
    0.07
    ?>"
    0.07
     '-')↵
    0.06
    realloc
    0.06
    .every
    0.06
    '))
↵
    0.06
     pageNo
    0.06
    Activations Density 0.023%

    No Known Activations