© 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. 80183
    Prev
    Next
    INDEX
    Explanations

    references to guilds and related organizations

    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
    er
    -0.07
    /respond
    -0.07
    adolu
    -0.06
    нд
    -0.06
     sayıda
    -0.06
    eing
    -0.06
    GenerationStrategy
    -0.06
    sealed
    -0.06
    ned
    -0.06
    eldon
    -0.06
    POSITIVE LOGITS
    crest
    0.09
    yard
    0.08
    mates
    0.08
    inary
    0.08
     crest
    0.08
    /un
    0.08
    sters
    0.08
    æ³ķ人
    0.07
    wagon
    0.07
    æ³Ĭ
    0.07
    Activations Density 0.002%

    No Known Activations