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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 2236
    Prev
    Next
    INDEX
    Explanations

    syntactical placeholders and metadata in structured documents or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vla
    -0.08
     IMPLIED
    -0.07
    )((((
    -0.07
    upertino
    -0.07
    jadi
    -0.06
    ?action
    -0.06
    tober
    -0.06
    ósito
    -0.06
    UpInside
    -0.06
     Gerard
    -0.06
    POSITIVE LOGITS
    airs
    0.07
    uff
    0.07
    .TryParse
    0.06
    ugs
    0.06
     Jak
    0.06
     sayılı
    0.06
    erna
    0.06
     Sayı
    0.06
     Mono
    0.06
    acks
    0.06
    Activations Density 0.136%

    No Known Activations