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. 84816
    Prev
    Next
    INDEX
    Explanations

    immune responses

    np_max-act · gemini-2.0-flash

    content related to vaccine development and immunogenicity.

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

    The neuron responds to immunology–related terms and phrases, especially those describing immune or immunogenic responses.

    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
    ultan
    -0.07
    uye
    -0.07
    -off
    -0.06
    acam
    -0.06
    ::*
    -0.06
    Movies
    -0.06
    entieth
    -0.06
    idores
    -0.06
    πτωση
    -0.06
    uros
    -0.06
    POSITIVE LOGITS
    mour
    0.07
    响
    0.07
     Sloven
    0.07
     reve
    0.07
     Lou
    0.07
    getic
    0.07
    (columns
    0.07
    _DRAW
    0.07
     ศ
    0.07
     blowing
    0.06
    Activations Density 0.011%

    No Known Activations