© 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. 82933
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to data, noise, or information processing

    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
    enor
    -0.08
    asha
    -0.08
    opensource
    -0.07
    гл
    -0.07
    ANTLR
    -0.07
     Ø¢Ùħ
    -0.07
    ampler
    -0.07
    ãn
    -0.07
    oints
    -0.07
    ây
    -0.07
    POSITIVE LOGITS
    (OP
    0.09
    /O
    0.08
    (O
    0.08
    (OS
    0.07
     Mell
    0.07
    å¯Ł
    0.06
     Gree
    0.06
    awa
    0.06
    ива
    0.06
     onRequest
    0.06
    Activations Density 0.447%

    No Known Activations