© 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. 95588
    Prev
    Next
    INDEX
    Explanations

    terms related to change and revisions

    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
    elopment
    -0.07
    anon
    -0.07
    enie
    -0.07
    ç¿Ĵ
    -0.07
    .Localization
    -0.07
    Mapped
    -0.07
    _mk
    -0.06
    µ
    -0.06
    _VC
    -0.06
    anonymous
    -0.06
    POSITIVE LOGITS
     retro
    0.07
     final
    0.07
    lich
    0.06
    forth
    0.06
     corrections
    0.06
     correction
    0.06
     correcting
    0.06
    elden
    0.06
     correct
    0.06
     Final
    0.06
    Activations Density 0.012%

    No Known Activations