© 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. 85580
    Prev
    Next
    INDEX
    Explanations

    references to data or information within a context

    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
    (es
    -0.08
    خاÙĨÙĩ
    -0.08
    our
    -0.07
    ÑģÑı
    -0.07
    jÅ¡ÃŃ
    -0.07
    ulant
    -0.07
    ding
    -0.07
    anner
    -0.06
    chers
    -0.06
    cription
    -0.06
    POSITIVE LOGITS
    nal
    0.09
    strup
    0.08
    ally
    0.08
    GenerationStrategy
    0.08
    aire
    0.07
    abel
    0.07
    éĩı
    0.07
    verity
    0.07
    .plist
    0.07
    aires
    0.07
    Activations Density 0.045%

    No Known Activations