© 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. 30203
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical data or statistics

    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
    oldt
    -0.07
     world
    -0.06
    estre
    -0.06
    ssc
    -0.06
     prime
    -0.06
     Turnbull
    -0.06
    mpl
    -0.05
     native
    -0.05
     subs
    -0.05
    820
    -0.05
    POSITIVE LOGITS
    ÃŃna
    0.08
    Ñģен
    0.07
    glyph
    0.07
    agua
    0.07
    RIORITY
    0.07
    tridge
    0.07
    agg
    0.06
    opsy
    0.06
    apes
    0.06
     ocas
    0.06
    Activations Density 0.007%

    No Known Activations