© 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 EvalsExportsAPI 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. 40423
    Prev
    Next
    INDEX
    Explanations

    specific formatting and styling properties in 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
     Broadcom
    -0.06
    enzyme
    -0.06
    chars
    -0.06
    þ
    -0.06
    rar
    -0.06
    æĭħ
    -0.06
    .dispatchEvent
    -0.06
    ajar
    -0.06
    rezent
    -0.06
    ä¸ĬãģĮ
    -0.06
    POSITIVE LOGITS
    .RELATED
    0.07
    .scalablytyped
    0.07
    ¤¤
    0.06
    apus
    0.06
    ilib
    0.06
    elden
    0.06
    unn
    0.06
     interp
    0.06
    unken
    0.06
    irs
    0.06
    Activations Density 0.013%

    No Known Activations