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. 85958
    Prev
    Next
    INDEX
    Explanations

    ide

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of sodium dodecyl sulfate–polyacrylamide gel electrophoresis (SDS-PAGE).

    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
     ca
    -0.07
    chin
    -0.07
    práv
    -0.07
     gripping
    -0.07
    ))).
    -0.07
    .Random
    -0.07
     embassy
    -0.06
     ringing
    -0.06
     folded
    -0.06
    cw
    -0.06
    POSITIVE LOGITS
    MainMenu
    0.07
     pInfo
    0.06
     licensors
    0.06
     mimeType
    0.06
    283
    0.06
     ніч
    0.06
    viewController
    0.06
     readFile
    0.06
     ActiveForm
    0.06
    _bbox
    0.06
    Activations Density 0.000%

    No Known Activations