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. 91108
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    discussions about sports management and fan involvement.

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

    The neuron chiefly responds to sequences of uppercase letters (acronyms or initialisms).

    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
     mathematics
    -0.06
    แบ
    -0.06
     věn
    -0.06
    .centerX
    -0.06
    .loop
    -0.06
     医
    -0.06
    .getJSONArray
    -0.06
    753
    -0.06
    テ
    -0.06
    英文
    -0.06
    POSITIVE LOGITS
     Hero
    0.07
    .Relative
    0.07
    ål
    0.07
     몰
    0.07
     Bir
    0.06
     Portfolio
    0.06
     THINK
    0.06
     Holy
    0.06
    alking
    0.06
    _trigger
    0.06
    Activations Density 0.067%

    No Known Activations