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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91923
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on identifiers of multimedia codecs or formats (e.g. “webp,” “decoder,” “vorbis,” “JPEG,” “MPEG4,” etc.).

    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
    PEndPoint
    -0.07
     love
    -0.06
     FONT
    -0.06
    ",↵↵
    -0.06
     Cut
    -0.06
    .CONTENT
    -0.06
    _ACT
    -0.06
    字段
    -0.06
     vow
    -0.06
    -yellow
    -0.06
    POSITIVE LOGITS
     대한민국
    0.08
    。此
    0.07
     enables
    0.06
     tallest
    0.06
     çıkar
    0.06
     arson
    0.06
     çalışma
    0.06
     الوص
    0.06
     Existing
    0.06
    .permissions
    0.06
    Activations Density 0.008%

    No Known Activations