© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44628
    Prev
    Next
    INDEX
    Explanations

    iris

    np_max-act · gemini-2.0-flash

    The neuron lights up on longer, domain‐specific or hyphenated technical terms (e.g. “alcohol-related,” “tumor marker,” “pgdb,” “Drosophila”).

    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
     Дмит
    -0.07
    .endpoint
    -0.06
    .mixin
    -0.06
    ervers
    -0.06
    анню
    -0.06
    Headers
    -0.06
     призна
    -0.06
     lakes
    -0.06
    !\
    -0.06
    .adapters
    -0.06
    POSITIVE LOGITS
     suede
    0.07
     uploaded
    0.06
     Sass
    0.06
     bize
    0.06
    urrection
    0.06
     Control
    0.06
     →↵↵
    0.06
    orgia
    0.06
    ,omitempty
    0.06
    agement
    0.06
    Activations Density 0.089%

    No Known Activations