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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93982
    Prev
    Next
    INDEX
    Explanations

    references to scientific research or publications

    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
     Russians
    -0.08
     Kremlin
    -0.07
    usz
    -0.07
    cz
    -0.06
     Russian
    -0.06
    691
    -0.06
    asz
    -0.06
     Warsaw
    -0.06
     Russia
    -0.06
     –
    -0.06
    POSITIVE LOGITS
    Ã¤ÃŁ
    0.08
    اخت
    0.07
    wyn
    0.07
    emer
    0.07
    chas
    0.07
    ccb
    0.07
    chest
    0.07
    خت
    0.07
    ektiv
    0.07
    ÐĶÐIJ
    0.06
    Activations Density 0.104%

    No Known Activations