© 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. 77514
    Prev
    Next
    INDEX
    Explanations

    references to the concept of exploration or the idea of uncovering deeper meanings

    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
    leme
    -0.08
    ÃŃÅ¡
    -0.07
     enclosure
    -0.07
    eldon
    -0.07
    annon
    -0.07
    _ENC
    -0.07
     Enc
    -0.07
    cÃŃ
    -0.06
    EDIA
    -0.06
    ETY
    -0.06
    POSITIVE LOGITS
     than
    0.09
     ello
    0.07
    efon
    0.07
    -than
    0.07
     Than
    0.07
    _than
    0.07
    _THAN
    0.07
    vinces
    0.07
    Than
    0.06
     THAN
    0.06
    Activations Density 0.004%

    No Known Activations