© 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. 107893
    Prev
    Next
    INDEX
    Explanations

    various coding structures and syntax elements

    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
    regor
    -0.07
    plnÄĽ
    -0.07
    yen
    -0.06
    ฺ
    -0.06
    afari
    -0.06
    hari
    -0.06
    aghan
    -0.06
    atk
    -0.06
    lap
    -0.06
    лиÑĪ
    -0.06
    POSITIVE LOGITS
     else
    0.14
     otherwise
    0.11
    	else
    0.11
     other
    0.11
    else
    0.10
     sonst
    0.09
    ãģĿãģ®ä»ĸ
    0.09
     anderen
    0.09
     finally
    0.09
    other
    0.09
    Activations Density 0.014%

    No Known Activations