© 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. 117589
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to mathematical and scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Reference identifiers in technical documents, typically linking to figures, equations, map coordinates, or program variables in academic papers, code, and documentation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    âĢ¦
    -0.06
     <->
    -0.05
     professional
    -0.05
     tarafından
    -0.05
     iron
    -0.05
    Âłin
    -0.05
    ,
    -0.05
    /ne
    -0.05
     officially
    -0.05
    abbit
    -0.04
    POSITIVE LOGITS
     اÙĦعظ
    0.10
    SCRIPTOR
    0.09
    ejména
    0.09
    .MixedReality
    0.09
    uitka
    0.09
    -wow
    0.09
    uju
    0.09
    formace
    0.09
    lacak
    0.09
    mlink
    0.09
    Activations Density 2.104%

    No Known Activations