© 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 EvalsExportsAPI 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. 126724
    Prev
    Next
    INDEX
    Explanations

    punctuation and date-related references

    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
    _Tis
    -0.07
    edia
    -0.07
    urette
    -0.07
    chw
    -0.07
    ɵ
    -0.07
    pector
    -0.07
    aster
    -0.07
    nga
    -0.07
    gom
    -0.07
    anyl
    -0.07
    POSITIVE LOGITS
     dark
    0.09
     Dark
    0.07
    iel
    0.07
     Onion
    0.07
    ÐļТ
    0.06
    IEL
    0.06
    dark
    0.06
    -dark
    0.06
     Hydra
    0.06
     DARK
    0.06
    Activations Density 0.000%

    No Known Activations