© 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. 81932
    Prev
    Next
    INDEX
    Explanations

    references to institutional affiliations and organizational structures

    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
    oram
    -0.07
    ja
    -0.06
    eden
    -0.06
    errs
    -0.06
     Forrest
    -0.06
    Äĥr
    -0.06
    /proto
    -0.06
    phony
    -0.05
    çłĤ
    -0.05
    emain
    -0.05
    POSITIVE LOGITS
    CJK
    0.08
    -toggler
    0.07
    FRING
    0.06
    canf
    0.06
    ÑĪÑĮ
    0.06
    Sizer
    0.06
    ãĤĩ
    0.06
    immel
    0.06
    ucker
    0.06
    onen
    0.06
    Activations Density 0.012%

    No Known Activations