© 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 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. 89229
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions and instructions about visual design processes

    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
     numbered
    -0.06
    owl
    -0.06
     great
    -0.06
     ephem
    -0.06
    ing
    -0.05
    lfw
    -0.05
     classics
    -0.05
     local
    -0.05
    Ol
    -0.05
     Overlay
    -0.05
    POSITIVE LOGITS
    ocha
    0.09
     Shields
    0.09
    央
    0.09
    ÃŃrk
    0.07
    yi
    0.07
    shield
    0.07
    ields
    0.07
     WHATSOEVER
    0.07
    unsch
    0.07
    æ±½
    0.07
    Activations Density 0.026%

    No Known Activations