© 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. 15-LLAMASCOPE-RES-131K
    11. 26818
    Prev
    Next
    INDEX
    Explanations

    references to business activities and expansions

    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
    wend
    -0.06
     usually
    -0.06
    ocity
    -0.06
     fier
    -0.06
    richt
    -0.06
     od
    -0.06
     account
    -0.06
    loor
    -0.06
     gum
    -0.06
    loo
    -0.06
    POSITIVE LOGITS
     THIS
    0.07
    084
    0.07
    =this
    0.06
    @update
    0.06
    .this
    0.06
    -this
    0.06
    imson
    0.06
    LARI
    0.06
    vably
    0.06
    ingo
    0.06
    Activations Density 0.015%

    No Known Activations