© 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. 77324
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statistics and reasoning related to renewable energy and its benefits

    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
     tact
    -0.06
    issy
    -0.06
    uffix
    -0.06
    SELL
    -0.06
     ********************************************************************************
    -0.06
     sph
    -0.06
    azor
    -0.06
     Mueller
    -0.06
     Kaiser
    -0.05
    oph
    -0.05
    POSITIVE LOGITS
    ijo
    0.08
    ombie
    0.07
    dech
    0.07
    nas
    0.07
     apl
    0.07
    urm
    0.06
    isini
    0.06
    ardown
    0.06
    umph
    0.06
    ooke
    0.06
    Activations Density 0.009%

    No Known Activations