© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128635
    Prev
    Next
    INDEX
    Explanations

    storytelling

    np_max-act · gemini-2.0-flash

    scientific terms and phrases related to medical treatments and protocols.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is sensitive to numeric expressions (especially decimals, percentages, and other measured values).

    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
    .notification
    -0.06
    _instruction
    -0.06
     Radar
    -0.06
    ird
    -0.06
    attery
    -0.06
    .assert
    -0.06
    .avatar
    -0.06
     hiss
    -0.06
    557
    -0.06
     Rc
    -0.06
    POSITIVE LOGITS
    ocused
    0.07
     uttered
    0.06
     neatly
    0.06
     endforeach
    0.06
     міста
    0.06
     réuss
    0.06
     visually
    0.06
     tanto
    0.06
     eigenen
    0.06
     identifiable
    0.06
    Activations Density 0.192%

    No Known Activations