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. 85391
    Prev
    Next
    INDEX
    Explanations

    scientific effects

    np_max-act · gemini-2.0-flash

    references to hormonal and biochemical mechanisms related to bodily functions and disease responses.

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

    This neuron fires on mentions of experimental outcomes or effects in scientific phrasing—e.g. words like “effect,” “inhibitory,” “mediated,” and “inhibition.”

    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
    -make
    -0.07
    _syn
    -0.07
    scores
    -0.06
     leh
    -0.06
     enlargement
    -0.06
     suffix
    -0.06
    administration
    -0.06
     represents
    -0.06
    Crit
    -0.06
    -proof
    -0.06
    POSITIVE LOGITS
    bourne
    0.07
    <string
    0.06
    .Toast
    0.06
    '}).
    0.06
    .examples
    0.06
    �
    0.06
     INCLUDING
    0.06
    _REFERER
    0.06
     ITEMS
    0.06
     José
    0.06
    Activations Density 0.052%

    No Known Activations