© 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. 106304
    Prev
    Next
    INDEX
    Explanations

    significant mentions of books and their impact

    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
    yk
    -0.07
    .pic
    -0.07
     sez
    -0.06
    isle
    -0.06
    SKU
    -0.06
    olson
    -0.06
    лава
    -0.06
    éĻµ
    -0.06
    _ARROW
    -0.06
    _tac
    -0.06
    POSITIVE LOGITS
    çħ§
    0.06
    íĻĢ
    0.06
    573
    0.06
    ento
    0.06
    ait
    0.06
    ojis
    0.05
     å»
    0.05
    /ref
    0.05
    403
    0.05
     ':
    0.05
    Activations Density 0.003%

    No Known Activations