© 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. 5-LLAMASCOPE-RES-131K
    11. 126554
    Prev
    Next
    INDEX
    Explanations

    references to competitive performance in sports

    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
    orrow
    -0.07
    folio
    -0.07
     numRows
    -0.07
    uell
    -0.07
    altung
    -0.06
    term
    -0.06
    amel
    -0.06
    FIELD
    -0.06
     Sug
    -0.06
    à¤Łà¤°
    -0.06
    POSITIVE LOGITS
    vetica
    0.07
    erer
    0.07
    boss
    0.07
    anst
    0.07
    onya
    0.06
     objectives
    0.06
    browser
    0.06
    zar
    0.06
    gan
    0.06
    /Math
    0.06
    Activations Density 0.096%

    No Known Activations