© 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. 76339
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and knowledge gaps

    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
    olle
    -0.08
    ãĥªãĤ¢
    -0.07
    atrix
    -0.06
    LEE
    -0.06
    ÑĢав
    -0.06
    lee
    -0.06
    anki
    -0.06
    èģĶç½ij
    -0.06
    ़ा
    -0.06
    /sweetalert
    -0.06
    POSITIVE LOGITS
     knowledge
    0.14
     known
    0.14
    knowledge
    0.12
     Knowledge
    0.12
     know
    0.12
    known
    0.12
     Known
    0.12
    Knowledge
    0.11
    -known
    0.11
     knew
    0.10
    Activations Density 0.186%

    No Known Activations