© 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 EvalsExportsinterp-engineNEWAPI 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. 79538
    Prev
    Next
    INDEX
    Explanations

    terms related to legal consequences and health impacts

    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
    erus
    -0.08
    ¨
    -0.07
    unto
    -0.07
    estre
    -0.07
    isen
    -0.07
    inox
    -0.06
    lage
    -0.06
    lew
    -0.06
    pla
    -0.06
     Fle
    -0.06
    POSITIVE LOGITS
    aar
    0.07
    æĢĢ
    0.06
     Sole
    0.06
     Cree
    0.06
    ides
    0.06
     Mobility
    0.06
    .opens
    0.06
     secondary
    0.06
    èij
    0.06
    getRow
    0.06
    Activations Density 0.036%

    No Known Activations