© 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. 93992
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic and athletic achievements

    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
    ibold
    -0.09
    aliz
    -0.07
    太éĥİ
    -0.07
    象
    -0.07
    ç»ĩ
    -0.07
    gi
    -0.07
    ulg
    -0.07
    reff
    -0.06
    èį·
    -0.06
    asking
    -0.06
    POSITIVE LOGITS
    pent
    0.07
    (er
    0.06
    acus
    0.06
    oya
    0.06
    iid
    0.06
    تÙĪر
    0.05
    innie
    0.05
    316
    0.05
    -Jan
    0.05
    ories
    0.05
    Activations Density 0.003%

    No Known Activations