© 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. 126806
    Prev
    Next
    INDEX
    Explanations

    references to online essays and philosophical content

    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
    chet
    -0.07
    Ìģt
    -0.07
    ãn
    -0.06
    é¬
    -0.06
    ollo
    -0.06
    inton
    -0.06
    arkin
    -0.06
    olest
    -0.06
    wend
    -0.05
    pline
    -0.05
    POSITIVE LOGITS
    ï¸
    0.08
    CEE
    0.08
    .com
    0.08
    .xmlbeans
    0.07
     Aires
    0.07
    fulWidget
    0.07
    OLOR
    0.07
     Alman
    0.07
     cancelButtonTitle
    0.07
     vess
    0.07
    Activations Density 0.038%

    No Known Activations