© 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. 125953
    Prev
    Next
    INDEX
    Explanations

    terms related to sporting finals and championships

    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
    onomy
    -0.07
    ularity
    -0.07
    annes
    -0.07
    atron
    -0.06
    efe
    -0.06
    154
    -0.06
    fulness
    -0.06
    pery
    -0.06
    bean
    -0.06
     Pry
    -0.06
    POSITIVE LOGITS
    ists
    0.09
    iram
    0.08
    tsy
    0.08
    ister
    0.08
    cial
    0.08
    ised
    0.08
    ities
    0.08
    ghan
    0.07
    -stage
    0.07
    mente
    0.07
    Activations Density 0.007%

    No Known Activations