© 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. 76560
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal counsel or representation

    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
    vet
    -0.08
    rende
    -0.07
    eya
    -0.07
    erd
    -0.07
     Dit
    -0.07
     nues
    -0.06
    edl
    -0.06
    maal
    -0.06
     Vet
    -0.06
    Accessor
    -0.06
    POSITIVE LOGITS
    ushi
    0.07
    anik
    0.06
    acement
    0.06
    ulin
    0.06
    اÙĬت
    0.06
    unj
    0.06
     Rarity
    0.06
     win
    0.06
    .foundation
    0.06
    ú
    0.06
    Activations Density 0.002%

    No Known Activations