© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125205
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements involving control flow and structure

    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
    mere
    -0.06
     mort
    -0.06
     low
    -0.06
    neas
    -0.06
    omb
    -0.06
    ick
    -0.06
     extra
    -0.06
     bist
    -0.06
     excess
    -0.06
    grave
    -0.06
    POSITIVE LOGITS
    çģ
    0.07
    oppel
    0.07
    addon
    0.07
    èĩ´
    0.07
     Cooler
    0.07
    igel
    0.07
    ----------------------------------------------------------------
    0.07
    ë°Ģ
    0.07
    rait
    0.07
    ahlen
    0.06
    Activations Density 0.017%

    No Known Activations