© 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. 76973
    Prev
    Next
    INDEX
    Explanations

    positive evaluations or justifications

    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
    ãĢħ
    -0.08
    oine
    -0.07
    geb
    -0.07
    .Interop
    -0.06
    nic
    -0.06
    UGE
    -0.06
    ì¦Ŀ
    -0.06
    ipel
    -0.06
     sple
    -0.06
    .Abstractions
    -0.06
    POSITIVE LOGITS
     ÑĤоже
    0.08
    ãĥ©ãĤ¯
    0.07
    emand
    0.07
    >\<
    0.06
    ossa
    0.06
    íĿ¥
    0.06
    vÄĽt
    0.06
    alic
    0.06
    vironments
    0.06
    udem
    0.06
    Activations Density 0.005%

    No Known Activations