© 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. 54746
    Prev
    Next
    INDEX
    Explanations

    descriptions of cultural or historical resources and their classifications

    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
    hv
    -0.08
    onen
    -0.07
    vais
    -0.07
    reh
    -0.07
    unya
    -0.07
    antan
    -0.07
    antis
    -0.07
    ackers
    -0.07
    rek
    -0.07
    engin
    -0.07
    POSITIVE LOGITS
     conc
    0.07
     works
    0.06
     Maher
    0.06
     bib
    0.06
     Brock
    0.06
     obras
    0.06
     attrib
    0.06
    UCT
    0.06
     --
    0.05
     mult
    0.05
    Activations Density 0.003%

    No Known Activations