© 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 EvalsExportsAPI 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. 125602
    Prev
    Next
    INDEX
    Explanations

    references to work and collaboration

    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
     Marilyn
    -0.07
    erk
    -0.07
    /from
    -0.07
    itamin
    -0.07
    quo
    -0.07
    ikel
    -0.06
     lẽ
    -0.06
    :CGRect
    -0.06
    gota
    -0.06
    elib
    -0.06
    POSITIVE LOGITS
    ilty
    0.07
     towards
    0.06
    éĵ¶
    0.06
     to
    0.06
    BI
    0.06
     Ward
    0.06
     Mechanics
    0.06
     communities
    0.06
     Tur
    0.06
    Clazz
    0.06
    Activations Density 0.014%

    No Known Activations