© 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. 89390
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to demographics and economic data

    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
    .EMPTY
    -0.07
    éri
    -0.07
     fewer
    -0.07
     ninh
    -0.07
    .GetUser
    -0.07
     λι
    -0.06
    BCM
    -0.06
     ìŀijìĿĢ
    -0.06
    adele
    -0.06
    eyim
    -0.06
    POSITIVE LOGITS
     naopak
    0.09
     broader
    0.08
     larger
    0.08
     much
    0.08
     wider
    0.08
     daleko
    0.08
     more
    0.08
     mnohem
    0.08
    deaux
    0.07
     bigger
    0.07
    Activations Density 0.042%

    No Known Activations