© 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. 87422
    Prev
    Next
    INDEX
    Explanations

    details related to book or document descriptions

    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
     paraph
    -0.06
    姿
    -0.06
     spin
    -0.06
    312
    -0.06
    anch
    -0.06
    bg
    -0.06
     spun
    -0.05
     immortal
    -0.05
     Version
    -0.05
    зÑĮ
    -0.05
    POSITIVE LOGITS
    nowled
    0.08
    ibel
    0.08
     FLOAT
    0.07
    sole
    0.07
     UNUSED
    0.07
    askell
    0.07
    erland
    0.07
     verso
    0.07
     front
    0.07
     Starr
    0.07
    Activations Density 0.004%

    No Known Activations