© 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. 72210
    Prev
    Next
    INDEX
    Explanations

    concepts related to involvement and complicity in actions or events

    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
    mus
    -0.07
    abal
    -0.07
    hora
    -0.06
     é¦
    -0.06
    èĭ
    -0.06
    ISS
    -0.06
    .DOM
    -0.06
    diet
    -0.06
     muscles
    -0.06
     iler
    -0.06
    POSITIVE LOGITS
     directly
    0.06
    /hooks
    0.06
     chain
    0.06
     mes
    0.06
     either
    0.06
     sk
    0.05
    iture
    0.05
     in
    0.05
     hook
    0.05
     å¯
    0.05
    Activations Density 0.012%

    No Known Activations