© 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. 62616
    Prev
    Next
    INDEX
    Explanations

    various forms of numeric ranges and comparisons

    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
    apa
    -0.06
    omb
    -0.06
    ata
    -0.06
    ibu
    -0.06
    1
    -0.05
     random
    -0.05
    910
    -0.05
    /text
    -0.05
    871
    -0.05
    iva
    -0.05
    POSITIVE LOGITS
    deaux
    0.09
    addir
    0.08
    AFX
    0.08
    andaÅŁ
    0.08
    pcodes
    0.07
    wdx
    0.07
    archical
    0.07
    SCALL
    0.07
     Ти
    0.07
    ncoder
    0.07
    Activations Density 0.043%

    No Known Activations