© 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. 82980
    Prev
    Next
    INDEX
    Explanations

    citations and references in scientific literature

    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
    /WebAPI
    -0.07
    адж
    -0.07
    кеÑĤ
    -0.06
    banks
    -0.06
    rug
    -0.06
    éra
    -0.06
     weight
    -0.06
    iland
    -0.06
    Offsets
    -0.06
    tank
    -0.06
    POSITIVE LOGITS
    orsch
    0.08
    oder
    0.08
    entionPolicy
    0.07
    оÑħ
    0.07
    isible
    0.07
    ียà¸Ļร
    0.07
    dek
    0.06
    ekt
    0.06
    /browse
    0.06
    ÐŁÑĸд
    0.06
    Activations Density 0.002%

    No Known Activations