© 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 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. 127486
    Prev
    Next
    INDEX
    Explanations

    connections or relationships between concepts

    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
    icken
    -0.08
     Freund
    -0.06
    ymph
    -0.06
    tet
    -0.06
    amen
    -0.06
     Dry
    -0.06
    hlen
    -0.06
    ammer
    -0.06
    opsis
    -0.06
    .Attributes
    -0.06
    POSITIVE LOGITS
    089
    0.08
    olas
    0.07
    utow
    0.07
    URN
    0.07
     Robbins
    0.07
    ISCO
    0.06
    emode
    0.06
     Kob
    0.06
    adla
    0.06
    PTY
    0.06
    Activations Density 0.001%

    No Known Activations