© 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. 62213
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming constructs

    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
    pill
    -0.08
    รม
    -0.07
    peria
    -0.07
    chein
    -0.06
    xl
    -0.06
    plor
    -0.06
    .named
    -0.06
    adian
    -0.06
    _ATOMIC
    -0.06
    ĥn
    -0.06
    POSITIVE LOGITS
     anything
    0.06
     telev
    0.06
    yw
    0.06
    ategorical
    0.06
    üç
    0.06
    getMock
    0.06
    anything
    0.06
     Ear
    0.05
    客
    0.05
     Sue
    0.05
    Activations Density 0.005%

    No Known Activations