© 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. 75277
    Prev
    Next
    INDEX
    Explanations

    references to graduates or alumni

    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
    anko
    -0.09
    ing
    -0.07
    ätt
    -0.07
    adolu
    -0.06
    izando
    -0.06
    ING
    -0.06
    ilyn
    -0.06
    ĩĮ
    -0.06
    bons
    -0.06
     Zem
    -0.06
    POSITIVE LOGITS
    604
    0.07
    ë¹ĦìķĦ
    0.07
    /current
    0.07
    na
    0.07
    ä¹ĭä¸Ģ
    0.06
    کز
    0.06
    querque
    0.06
     Åŀu
    0.06
    hip
    0.06
     pacing
    0.06
    Activations Density 0.003%

    No Known Activations