© 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. 106543
    Prev
    Next
    INDEX
    Explanations

    references to media-related content

    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
    orman
    -0.07
    uden
    -0.07
    иÑĤа
    -0.07
    unnel
    -0.07
    building
    -0.07
    Disclosure
    -0.07
    èªŃ
    -0.07
    reads
    -0.07
    .dtd
    -0.07
    gs
    -0.06
    POSITIVE LOGITS
    eval
    0.09
    arda
    0.07
     Qu
    0.07
     scr
    0.07
    753
    0.06
    istar
    0.06
    /media
    0.06
    enor
    0.06
    /File
    0.06
    vine
    0.06
    Activations Density 0.013%

    No Known Activations