© 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. 75309
    Prev
    Next
    INDEX
    Explanations

    expressions of approval or positive observation

    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
    Override
    -0.07
    ienie
    -0.07
    omen
    -0.07
    eman
    -0.06
    owed
    -0.06
    cio
    -0.06
    orman
    -0.06
    ÑĮми
    -0.06
    ìĹIJê²Į
    -0.06
    uese
    -0.06
    POSITIVE LOGITS
    iqueta
    0.07
    å¦ĤæѤ
    0.07
    è¿Ļä¹Ī
    0.07
    how
    0.07
     how
    0.07
     bahwa
    0.07
    ç«Ł
    0.06
     someone
    0.06
    üss
    0.06
     such
    0.06
    Activations Density 0.010%

    No Known Activations