© 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. 62216
    Prev
    Next
    INDEX
    Explanations

    specific non-English characters or symbols

    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
    pt
    -0.07
    íı¬
    -0.07
    bes
    -0.07
    icos
    -0.07
    oret
    -0.07
    bble
    -0.07
    aging
    -0.07
    433
    -0.06
    incer
    -0.06
     Harden
    -0.06
    POSITIVE LOGITS
     propos
    0.07
    erosis
    0.07
    eus
    0.07
    installer
    0.07
    elik
    0.07
    unner
    0.07
    longleftrightarrow
    0.06
    isque
    0.06
    asics
    0.06
    ugg
    0.06
    Activations Density 0.006%

    No Known Activations