© 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. 78532
    Prev
    Next
    INDEX
    Explanations

    facts and information related to animal care and characteristics

    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
    asco
    -0.09
    ográf
    -0.08
    кÑģ
    -0.07
    .kr
    -0.07
    UDA
    -0.07
    steen
    -0.07
    ymoon
    -0.07
    thora
    -0.07
    hawk
    -0.07
    agra
    -0.07
    POSITIVE LOGITS
     hypo
    0.07
     companion
    0.07
     breed
    0.06
     mans
    0.06
     AK
    0.06
    elter
    0.06
     coat
    0.06
     floppy
    0.06
     Toy
    0.06
     body
    0.06
    Activations Density 0.019%

    No Known Activations