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. 130378
    Prev
    Next
    INDEX
    Explanations

    Enclosing/attaching parts

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of specific physical device components (e.g. cover, body) in technical or patent‐style descriptions.

    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
     insults
    -0.07
     Tobacco
    -0.06
     films
    -0.06
     Gates
    -0.06
     entertainment
    -0.06
     auction
    -0.06
    video
    -0.06
    接
    -0.06
    ithe
    -0.06
    jury
    -0.06
    POSITIVE LOGITS
    arda
    0.07
     slick
    0.07
     Kanun
    0.07
    artifact
    0.07
    _shell
    0.06
    -be
    0.06
    .priv
    0.06
    #undef
    0.06
    -NLS
    0.06
     staffer
    0.06
    Activations Density 0.035%

    No Known Activations