© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61177
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "or" in relation to time periods or alternatives

    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
    gaard
    -0.10
    onica
    -0.09
    viÄį
    -0.08
    %A
    -0.07
    Äĥn
    -0.07
    gency
    -0.07
    iode
    -0.07
    pei
    -0.07
     aray
    -0.07
    arResult
    -0.07
    POSITIVE LOGITS
     possibly
    0.08
     earliest
    0.08
     maybe
    0.08
     early
    0.07
     perhaps
    0.07
    maybe
    0.07
     earlier
    0.07
     sooner
    0.07
    possibly
    0.06
     else
    0.06
    Activations Density 0.006%

    No Known Activations