© 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. 1953
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or metrics

    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
    ayah
    -0.08
    ãģ£
    -0.07
    еÑģÑı
    -0.07
    addin
    -0.07
    bidden
    -0.07
    ksiyon
    -0.07
    .volley
    -0.07
    ÏĦÏĤ
    -0.07
    ÅĻiv
    -0.07
    볬
    -0.07
    POSITIVE LOGITS
     pur
    0.08
     suggests
    0.07
     tell
    0.07
     allows
    0.07
     sug
    0.07
     says
    0.07
     tells
    0.06
     pros
    0.06
    æīĢ
    0.06
     allow
    0.06
    Activations Density 0.018%

    No Known Activations