© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74286
    Prev
    Next
    INDEX
    Explanations

    references to community involvement and demographics

    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
    idor
    -0.07
    orias
    -0.07
    grav
    -0.07
    ENDOR
    -0.07
    ancias
    -0.06
     whats
    -0.06
    vore
    -0.06
     stuff
    -0.06
    iefs
    -0.06
    alar
    -0.06
    POSITIVE LOGITS
     whose
    0.12
     who
    0.10
    whose
    0.09
    who
    0.09
     that
    0.08
     коÑĤоÑĢÑĭе
    0.08
    qui
    0.08
     коÑĤоÑĢаÑı
    0.07
     kteÅĻÃŃ
    0.07
     коÑĤоÑĢÑĭй
    0.07
    Activations Density 0.035%

    No Known Activations