© 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. 84404
    Prev
    Next
    INDEX
    Explanations

    code-related commands and error messages

    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
     (
    -0.06
    illard
    -0.06
    dao
    -0.06
     Hao
    -0.06
    yl
    -0.06
    ello
    -0.06
    vent
    -0.05
    verse
    -0.05
    cox
    -0.05
    avel
    -0.05
    POSITIVE LOGITS
     nackte
    0.08
    _fixture
    0.08
    edback
    0.08
    ##_
    0.07
    emachine
    0.07
     undermin
    0.07
    URAL
    0.07
    /*č↵
    0.07
    лаж
    0.07
    |{↵
    0.07
    Activations Density 0.001%

    No Known Activations