© 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. 17937
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistical comparisons about demographics

    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
    otime
    -0.08
    Porno
    -0.07
    iena
    -0.07
    -addon
    -0.07
    isku
    -0.07
    eldorf
    -0.07
    /apt
    -0.07
    é¡Ķ
    -0.07
    erce
    -0.07
     QSize
    -0.07
    POSITIVE LOGITS
     мÑĥжÑĩин
    0.06
     gangbang
    0.06
    istrovstvÃŃ
    0.06
     ratios
    0.05
     healthy
    0.05
     bob
    0.05
     continuity
    0.05
    984
    0.05
     oto
    0.05
    -scalable
    0.05
    Activations Density 0.001%

    No Known Activations