© 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. 60630
    Prev
    Next
    INDEX
    Explanations

    terms related to energy, environmental projects, and funding initiatives

    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
     weakening
    -0.06
    kills
    -0.06
    contre
    -0.06
    貨
    -0.06
    @student
    -0.06
     aproxim
    -0.06
    aleza
    -0.06
    perimental
    -0.06
     zastup
    -0.06
     sweeps
    -0.06
    POSITIVE LOGITS
     still
    0.08
     finally
    0.07
     STILL
    0.07
     sp
    0.06
     again
    0.06
    ARING
    0.06
     sn
    0.06
     gr
    0.06
     ie
    0.06
    deen
    0.06
    Activations Density 0.309%

    No Known Activations