© 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. 85532
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to temperature and physical sensations

    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
    luž
    -0.07
    etÃŃ
    -0.07
    olute
    -0.07
    odzi
    -0.07
    mtree
    -0.07
    ÑĢож
    -0.07
     nouve
    -0.06
    reature
    -0.06
    EATURE
    -0.06
    élé
    -0.06
    POSITIVE LOGITS
     Firm
    0.07
     firm
    0.06
    acco
    0.06
     readily
    0.06
     depression
    0.06
    622
    0.06
    ICA
    0.06
     Interr
    0.06
     fing
    0.06
    ulin
    0.06
    Activations Density 0.014%

    No Known Activations