© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89802
    Prev
    Next
    INDEX
    Explanations

    references to data files and documentation

    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
    amo
    -0.06
    egra
    -0.06
     Hen
    -0.06
    erson
    -0.06
    asp
    -0.06
    benh
    -0.06
    864
    -0.05
    651
    -0.05
    ulla
    -0.05
     specialists
    -0.05
    POSITIVE LOGITS
    yms
    0.08
    ãİ
    0.08
    UGIN
    0.08
    #ad
    0.07
     CONSEQUENTIAL
    0.07
    ìĸij
    0.07
    readcr
    0.07
    üml
    0.07
    ebek
    0.07
     Lon
    0.07
    Activations Density 0.003%

    No Known Activations