© 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. 76305
    Prev
    Next
    INDEX
    Explanations

    references to exhibitions

    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
    otate
    -0.08
    zon
    -0.08
    ÑĪев
    -0.07
     ((__
    -0.07
     prod
    -0.07
    ffect
    -0.07
     (*((
    -0.07
    cher
    -0.07
    zo
    -0.07
    kits
    -0.07
    POSITIVE LOGITS
    ively
    0.08
    929
    0.08
    matic
    0.07
    /import
    0.07
    tee
    0.07
    etten
    0.07
    oft
    0.07
    æŁľ
    0.07
    crement
    0.07
    uters
    0.07
    Activations Density 0.015%

    No Known Activations