© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119028
    Prev
    Next
    INDEX
    Explanations

    mathematical and physical parameters in equations

    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
     ydk
    -0.07
    pson
    -0.07
    нÑĸÑĪ
    -0.07
    á»ĵ
    -0.07
    warts
    -0.07
    asco
    -0.07
     |_
    -0.06
    eper
    -0.06
    rowning
    -0.06
    containers
    -0.06
    POSITIVE LOGITS
     thousand
    0.07
    idia
    0.07
    0.06
    éģł
    0.06
     Ced
    0.06
    inth
    0.06
    ibel
    0.06
    aggio
    0.06
    ivas
    0.06
    rut
    0.05
    Activations Density 0.031%

    No Known Activations