© 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. 62392
    Prev
    Next
    INDEX
    Explanations

    expressions conveying relative comparisons or contrasts

    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
     indeed
    -0.07
    enberg
    -0.06
    coni
    -0.06
     not
    -0.06
    Ø°
    -0.06
    äs
    -0.06
    asher
    -0.06
    enburg
    -0.06
     Zar
    -0.05
     dis
    -0.05
    POSITIVE LOGITS
     anymore
    0.12
     necessarily
    0.11
    éĤ£ä¹Ī
    0.11
     tolik
    0.10
     tão
    0.09
     ê·¸ëłĩ
    0.07
    urt
    0.07
    orian
    0.07
    nor
    0.07
     à¤ĩतन
    0.07
    Activations Density 0.065%

    No Known Activations