Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5278
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and professional backgrounds

    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
    anca
    -0.07
    igrate
    -0.07
    roker
    -0.06
    inya
    -0.06
     ged
    -0.06
    inu
    -0.06
    asley
    -0.06
    uya
    -0.06
    umba
    -0.06
    alendar
    -0.06
    POSITIVE LOGITS
     taught
    0.21
     teach
    0.16
     teaches
    0.16
     teaching
    0.15
     Teach
    0.12
    æķĻ
    0.12
     Teaching
    0.11
     teachings
    0.11
     prepares
    0.11
     ense
    0.11
    Activations Density 0.044%

    No Known Activations