© 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. 104773
    Prev
    Next
    INDEX
    Explanations

    references to academic articles and papers, particularly their metadata

    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
    ablo
    -0.06
    oins
    -0.06
    oard
    -0.06
    ола
    -0.06
    reeze
    -0.06
     Kens
    -0.06
    ilst
    -0.06
    oxide
    -0.06
    ssp
    -0.06
    ssel
    -0.06
    POSITIVE LOGITS
    imit
    0.06
    ym
    0.06
    MainMenu
    0.06
    lik
    0.06
    owie
    0.06
    anity
    0.06
    Crop
    0.06
    quia
    0.06
    uncio
    0.06
    udd
    0.06
    Activations Density 0.013%

    No Known Activations