© 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. 27436
    Prev
    Next
    INDEX
    Explanations

    phrases related to features and specifications

    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
     ActionTypes
    -0.07
    psilon
    -0.07
    mort
    -0.07
    htm
    -0.07
    Atoms
    -0.06
    xBC
    -0.06
    ALE
    -0.06
    gaard
    -0.06
    eus
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    POSITIVE LOGITS
     revert
    0.07
    /default
    0.07
    eer
    0.06
    usters
    0.06
    itionally
    0.06
     reverted
    0.06
    ôn
    0.06
    uchs
    0.06
    .Compiler
    0.06
    mente
    0.06
    Activations Density 0.003%

    No Known Activations