© 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. 15-LLAMASCOPE-RES-131K
    11. 86737
    Prev
    Next
    INDEX
    Explanations

    references to biological processes and health-related concepts

    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
    elles
    -0.08
    arih
    -0.07
    toi
    -0.07
    dum
    -0.06
    angl
    -0.06
    rame
    -0.06
    اÙħÙĬ
    -0.06
    activex
    -0.06
     supporting
    -0.06
    zel
    -0.06
    POSITIVE LOGITS
    iana
    0.06
    ulp
    0.06
    joy
    0.06
    lings
    0.06
     Heights
    0.06
    andi
    0.06
    igh
    0.06
     stimuli
    0.06
    ään
    0.06
    jug
    0.06
    Activations Density 0.023%

    No Known Activations