© 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. 29218
    Prev
    Next
    INDEX
    Explanations

    expressions of physical sensations and body language

    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
    cps
    -0.07
     yat
    -0.07
    ÙĪÙĤ
    -0.07
     koup
    -0.07
    hoe
    -0.06
    entina
    -0.06
    cmc
    -0.06
    PLAIN
    -0.06
    aines
    -0.06
     bel
    -0.06
    POSITIVE LOGITS
    åIJĪåIJĮ
    0.06
    erot
    0.06
     Sag
    0.06
    .Release
    0.06
    usters
    0.06
     against
    0.06
     eyebrows
    0.06
     Buster
    0.06
    contro
    0.05
    ±
    0.05
    Activations Density 0.012%

    No Known Activations