© 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. 118750
    Prev
    Next
    INDEX
    Explanations

    references to waiting or delays

    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
    èĤ¯
    -0.07
    utherland
    -0.06
     ↵↵
    -0.06
    амеÑĤ
    -0.06
    ParameterValue
    -0.06
     Crew
    -0.06
    ImageData
    -0.06
    ISC
    -0.06
    Âłmi
    -0.06
    reff
    -0.06
    POSITIVE LOGITS
    amina
    0.08
    å§ĵ
    0.07
    änd
    0.07
    uml
    0.07
    antro
    0.07
    ontology
    0.07
    amin
    0.07
    -regexp
    0.07
    azi
    0.06
    '"
    0.06
    Activations Density 0.000%

    No Known Activations