© 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. 75157
    Prev
    Next
    INDEX
    Explanations

    references to nighttime scenery and celestial elements

    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
     ÙĪز
    -0.07
     underwater
    -0.07
     سبز
    -0.06
    eam
    -0.06
     नर
    -0.06
     Za
    -0.06
    monkey
    -0.06
    ATER
    -0.06
    uais
    -0.06
    _MR
    -0.06
    POSITIVE LOGITS
     stars
    0.11
     nights
    0.10
     night
    0.10
     Stars
    0.09
     star
    0.09
    stars
    0.09
     tonight
    0.08
    -stars
    0.08
     naked
    0.08
     Star
    0.07
    Activations Density 0.014%

    No Known Activations