© 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. 38958
    Prev
    Next
    INDEX
    Explanations

    references to groups or collectives

    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
    hone
    -0.09
    igua
    -0.08
    pany
    -0.08
    롱
    -0.07
    eri
    -0.07
    unas
    -0.07
    chl
    -0.07
    пон
    -0.07
    ider
    -0.07
    लत
    -0.07
    POSITIVE LOGITS
    ings
    0.13
    think
    0.10
    usc
    0.09
    sWith
    0.09
    atsby
    0.09
    roupon
    0.08
    abouts
    0.08
    sters
    0.08
    mates
    0.07
    manship
    0.07
    Activations Density 0.055%

    No Known Activations