© 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. 9-LLAMASCOPE-RES-131K
    11. 94446
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to numbering and sequences

    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
    LEAN
    -0.06
    pez
    -0.06
    _compiler
    -0.06
     Kramer
    -0.06
     mr
    -0.06
    pta
    -0.05
    924
    -0.05
    est
    -0.05
     force
    -0.05
    force
    -0.05
    POSITIVE LOGITS
    'gc
    0.07
    碼
    0.07
    ued
    0.07
    anoia
    0.07
    íĻĶ
    0.07
     bowel
    0.07
    athed
    0.06
    progressbar
    0.06
    }}],↵
    0.06
    à¸ļร
    0.06
    Activations Density 0.016%

    No Known Activations