© 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. 15-LLAMASCOPE-RES-131K
    11. 86952
    Prev
    Next
    INDEX
    Explanations

    statements about possibilities and uncertainties

    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
    imo
    -0.07
    onda
    -0.07
    ansa
    -0.07
    itten
    -0.06
    hlen
    -0.06
     professions
    -0.06
    .future
    -0.06
    æ³Ľ
    -0.06
     Dir
    -0.06
    ugar
    -0.06
    POSITIVE LOGITS
     unpredict
    0.07
    nop
    0.07
     surprises
    0.07
    еÑĢÑĤ
    0.07
    uai
    0.07
    hend
    0.06
    heed
    0.06
    rin
    0.06
    uries
    0.06
     computers
    0.06
    Activations Density 0.022%

    No Known Activations