© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3316
    Prev
    Next
    INDEX
    Explanations

    key terms related to institutional frameworks and educational structures

    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
    ighton
    -0.07
    inya
    -0.07
    olo
    -0.07
    æĪĸèĢħ
    -0.07
    ìĿ´ëĤĺ
    -0.07
     or
    -0.07
    ê±°ëĤĺ
    -0.07
    ori
    -0.07
    icha
    -0.07
    nick
    -0.06
    POSITIVE LOGITS
     whereas
    0.07
    ãģ¾ãĤĬ
    0.07
     ayrıca
    0.07
     along
    0.07
    mess
    0.07
     Ø£ÙĬض
    0.06
     Also
    0.06
     Whereas
    0.06
     غر
    0.06
    ensi
    0.06
    Activations Density 0.056%

    No Known Activations