© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    symbols, numerical values, and indicators of metadata

    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
     gang
    -0.06
    ix
    -0.06
    eler
    -0.06
    ë°
    -0.06
     craz
    -0.05
     justification
    -0.05
    ength
    -0.05
    ilm
    -0.05
     stranger
    -0.05
    iken
    -0.05
    POSITIVE LOGITS
    langs
    0.08
    ampie
    0.08
    kee
    0.08
    inou
    0.07
    axy
    0.07
     title
    0.07
     Tento
    0.07
    »:
    0.07
    ovu
    0.07
    .Arg
    0.07
    Activations Density 0.033%

    No Known Activations