© 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. 126036
    Prev
    Next
    INDEX
    Explanations

    articles indicating significance or achievements 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
    737
    -0.06
    ursor
    -0.06
    553
    -0.06
    qid
    -0.06
    chine
    -0.06
    osal
    -0.06
    æ½
    -0.06
    753
    -0.06
    _die
    -0.06
    ensex
    -0.06
    POSITIVE LOGITS
    हन
    0.07
    asso
    0.06
    division
    0.06
    izzo
    0.06
    ucken
    0.06
    Division
    0.06
    areth
    0.06
    ané
    0.06
    imit
    0.06
     division
    0.06
    Activations Density 0.004%

    No Known Activations