© 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. 73957
    Prev
    Next
    INDEX
    Explanations

    references to organizations and project names

    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
     to
    -0.07
     in
    -0.07
    -0.07
     from
    -0.07
     (
    -0.06
     last
    -0.06
     as
    -0.06
    amin
    -0.06
     while
    -0.06
     Grim
    -0.06
    POSITIVE LOGITS
     ActionTypes
    0.10
     ReturnType
    0.08
    idel
    0.08
     çī
    0.08
     COPYRIGHT
    0.08
    copyright
    0.08
    ©
    0.08
     ©
    0.08
    Copyright
    0.08
    .Îł
    0.07
    Activations Density 0.012%

    No Known Activations