© 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. 76446
    Prev
    Next
    INDEX
    Explanations

    configuration settings in software 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
    olk
    -0.06
     Baby
    -0.05
    .module
    -0.05
     round
    -0.05
    StateMachine
    -0.05
     coinc
    -0.05
     Pearl
    -0.05
     form
    -0.05
     xét
    -0.05
    èķ
    -0.05
    POSITIVE LOGITS
     Arguments
    0.09
    _OPTS
    0.09
     flags
    0.08
    flags
    0.08
     Args
    0.08
    arguments
    0.08
    Arguments
    0.08
    _args
    0.07
     arguments
    0.07
     args
    0.07
    Activations Density 0.060%

    No Known Activations