© 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. 41915
    Prev
    Next
    INDEX
    Explanations

    references to supportive resources or communities

    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
    @nate
    -0.08
    .UnitTesting
    -0.08
    otics
    -0.07
    era
    -0.07
    lec
    -0.07
    acades
    -0.06
    lod
    -0.06
     οÏĢο
    -0.06
     pha
    -0.06
    icl
    -0.06
    POSITIVE LOGITS
     how
    0.14
    how
    0.10
     its
    0.09
     what
    0.09
     why
    0.09
     cómo
    0.08
     plus
    0.08
     hvordan
    0.07
     How
    0.07
    erre
    0.07
    Activations Density 0.015%

    No Known Activations