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. 130518
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of “chimera” or “chimeric,” i.e. mentions of chimeric constructs or proteins.

    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
    -settings
    -0.07
    .submit
    -0.06
     Shar
    -0.06
    '})
    -0.06
    .med
    -0.06
    越
    -0.06
    .bind
    -0.06
    .gwt
    -0.06
     thunk
    -0.06
    FileType
    -0.06
    POSITIVE LOGITS
    Train
    0.06
    プリ
    0.06
    prü
    0.06
    swick
    0.06
    coord
    0.06
    境
    0.06
     Peb
    0.06
    .opacity
    0.06
    τογραφ
    0.06
     v
    0.06
    Activations Density 0.023%

    No Known Activations