© 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. 124606
    Prev
    Next
    INDEX
    Explanations

    terms related to support or assistance

    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
    à¸ĵ
    -0.08
    adden
    -0.08
    earch
    -0.08
    ales
    -0.07
    isher
    -0.07
    isce
    -0.07
    swick
    -0.07
    italize
    -0.07
    csv
    -0.07
    eper
    -0.07
    POSITIVE LOGITS
    uring
    0.08
    ailable
    0.07
    ass
    0.07
    ive
    0.07
    ena
    0.07
    OCI
    0.07
    sembl
    0.07
    linger
    0.07
    enza
    0.06
    ively
    0.06
    Activations Density 0.011%

    No Known Activations