Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 104075
    Prev
    Next
    INDEX
    Explanations

    setObject/Object

    np_max-act · gemini-2.0-flash

    code snippets related to iOS app development and technical questions.

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

    This neuron responds to Objective-C message sends, i.e. method-call selector names in bracketed calls.

    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
    _ENCOD
    -0.07
    ewidth
    -0.07
     ghi
    -0.07
    .Build
    -0.07
     assurance
    -0.07
     Cleans
    -0.06
     Newsp
    -0.06
    >Last
    -0.06
     pursuit
    -0.06
     mails
    -0.06
    POSITIVE LOGITS
     cuer
    0.06
    ้านด
    0.06
    PH
    0.06
    career
    0.06
    ــــ
    0.06
     sợ
    0.06
    xEA
    0.06
    ################
    0.06
    :@{
    0.06
     *)[
    0.06
    Activations Density 0.002%

    No Known Activations