© 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. 15-LLAMASCOPE-RES-131K
    11. 61892
    Prev
    Next
    INDEX
    Explanations

    instances of collaboration and requests for input or feedback

    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
    antal
    -0.07
    855
    -0.07
    ean
    -0.07
    iid
    -0.07
    INavigation
    -0.07
    otton
    -0.07
    Ñĩен
    -0.07
     '&#
    -0.07
    .sep
    -0.07
    [array
    -0.07
    POSITIVE LOGITS
     additional
    0.08
     contributed
    0.07
     contribution
    0.07
     ideas
    0.07
     contributions
    0.07
     suggested
    0.07
     help
    0.07
     contribute
    0.06
     other
    0.06
     alternative
    0.06
    Activations Density 0.075%

    No Known Activations