© 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. 17-LLAMASCOPE-RES-131K
    11. 86779
    Prev
    Next
    INDEX
    Explanations

    terms related to observing or noting particular details or phenomena

    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
    ean
    -0.07
    ackers
    -0.07
    lite
    -0.07
    estre
    -0.06
    _PARAMS
    -0.06
    arian
    -0.06
    Ñľ
    -0.06
    auer
    -0.06
    asco
    -0.06
    dl
    -0.06
    POSITIVE LOGITS
    tÃŃ
    0.07
    buz
    0.06
    tom
    0.06
     connected
    0.06
     dequeueReusableCellWithIdentifier
    0.06
     about
    0.06
    çķª
    0.06
     ANT
    0.06
    722
    0.05
    prak
    0.05
    Activations Density 0.000%

    No Known Activations