© 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. 75299
    Prev
    Next
    INDEX
    Explanations

    specific historical dates and military ranks

    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
    Enlarge
    -0.07
    ÑħÑĸд
    -0.07
    892
    -0.07
    ritz
    -0.07
    Äįem
    -0.07
     Æ°á»Ľc
    -0.06
    urdy
    -0.06
    \base
    -0.06
    AEA
    -0.06
    æ³
    -0.06
    POSITIVE LOGITS
    engu
    0.07
     lại
    0.07
     redesign
    0.06
     elevation
    0.06
     fist
    0.06
    ħį
    0.06
    ense
    0.06
     promotion
    0.06
    tas
    0.06
     Fist
    0.06
    Activations Density 0.009%

    No Known Activations