© 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. 29685
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to buttons and iconography

    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
    gar
    -0.07
    ãģ£ãģ¡
    -0.07
    ract
    -0.07
    enek
    -0.06
    /archive
    -0.06
    unch
    -0.06
     siti
    -0.06
    æ¸Ī
    -0.06
    aqu
    -0.06
    BST
    -0.06
    POSITIVE LOGITS
    ZA
    0.07
     termed
    0.06
    ÅĻad
    0.06
    ï¸
    0.06
    avr
    0.06
    iasm
    0.06
    adies
    0.06
     Span
    0.06
    ync
    0.06
    idas
    0.06
    Activations Density 0.011%

    No Known Activations