© 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 EvalsExportsinterp-engineNEWAPI 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. 17991
    Prev
    Next
    INDEX
    Explanations

    instructions related to managing a clipboard or user interface elements

    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
    å®Ī
    -0.06
     ÑĩÑĤ
    -0.06
    oid
    -0.06
     Industries
    -0.06
     compartment
    -0.06
     strong
    -0.06
    eth
    -0.06
     channels
    -0.06
    con
    -0.06
    âĢ
    -0.06
    POSITIVE LOGITS
    .yahoo
    0.09
    Parms
    0.08
    _parm
    0.08
     onLoad
    0.08
    Fcn
    0.08
    -------------</
    0.08
    Buzz
    0.07
    opher
    0.07
    luž
    0.07
    Sizer
    0.07
    Activations Density 0.003%

    No Known Activations