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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105187
    Prev
    Next
    INDEX
    Explanations

    queries and evaluations regarding opinions or experiences

    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
    rif
    -0.06
     Kür
    -0.06
     Leer
    -0.06
    iants
    -0.06
    okus
    -0.06
    upo
    -0.06
    âu
    -0.06
    Įĵ
    -0.06
    Æ°Æ¡ng
    -0.06
    frey
    -0.06
    POSITIVE LOGITS
     why
    0.17
     reasons
    0.15
    why
    0.14
     Why
    0.14
    Why
    0.13
     Reasons
    0.13
     reason
    0.12
     WHY
    0.12
    reason
    0.11
    _reason
    0.11
    Activations Density 0.056%

    No Known Activations