© 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. 120513
    Prev
    Next
    INDEX
    Explanations

    terms related to editorial content and responsibilities

    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
    erval
    -0.07
    ely
    -0.07
    ema
    -0.07
    764
    -0.07
    ech
    -0.07
    edges
    -0.07
    emes
    -0.07
    enal
    -0.07
    kinson
    -0.07
    egr
    -0.07
    POSITIVE LOGITS
    izes
    0.08
    ised
    0.07
    ignum
    0.07
    monds
    0.07
    ieee
    0.06
     Vacuum
    0.06
    icerca
    0.06
    ises
    0.06
     committee
    0.06
    ãĤ¹ãĥ¬
    0.06
    Activations Density 0.003%

    No Known Activations