© 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. 71522
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proximity or near-ness

    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
    orer
    -0.07
    опаÑģ
    -0.07
    allery
    -0.07
    xor
    -0.07
    oran
    -0.07
    ÑĢава
    -0.06
     Odyssey
    -0.06
    ints
    -0.06
    orem
    -0.06
    utf
    -0.06
    POSITIVE LOGITS
     complete
    0.09
     completely
    0.09
     entirely
    0.08
     identical
    0.08
     impossible
    0.08
     perfect
    0.08
    elden
    0.07
     entire
    0.07
     exclusively
    0.07
     virtually
    0.07
    Activations Density 0.026%

    No Known Activations