© 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. 117420
    Prev
    Next
    INDEX
    Explanations

    expressions of contrast and complexity

    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
    ÙĬÙĤ
    -0.06
     beyond
    -0.06
    itel
    -0.06
    inci
    -0.06
     liebe
    -0.06
    lick
    -0.06
    lov
    -0.06
     Verfüg
    -0.06
     Millennium
    -0.05
    λή
    -0.05
    POSITIVE LOGITS
     otherwise
    0.20
    otherwise
    0.17
     OTHERWISE
    0.16
     Otherwise
    0.16
    Otherwise
    0.15
     sonst
    0.10
     jinak
    0.09
     else
    0.09
     other
    0.08
    åIJ¦
    0.08
    Activations Density 0.037%

    No Known Activations