© 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. 87167
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "wheat."

    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
    rq
    -0.07
    acity
    -0.07
    thon
    -0.07
    asca
    -0.07
    ots
    -0.06
    incinn
    -0.06
    ½Ķ
    -0.06
    regon
    -0.06
    ouve
    -0.06
    εβ
    -0.06
    POSITIVE LOGITS
    rough
    0.08
    Sharper
    0.07
    ILD
    0.07
    Ä±ÅŁÄ±
    0.07
    acom
    0.07
     germ
    0.07
    ishes
    0.07
    iful
    0.07
    field
    0.07
     Newman
    0.07
    Activations Density 0.003%

    No Known Activations