© 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. 9-LLAMASCOPE-RES-131K
    11. 97838
    Prev
    Next
    INDEX
    Explanations

    terms related to data loading and resource management in programming

    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
    /how
    -0.08
    /all
    -0.08
    /her
    -0.07
    loating
    -0.07
    bread
    -0.07
    Ware
    -0.06
    наÑĢод
    -0.06
    quam
    -0.06
    ÑĪ
    -0.06
    /left
    -0.06
    POSITIVE LOGITS
    edException
    0.09
    ings
    0.08
    iciel
    0.08
    edImage
    0.08
    mate
    0.07
    .AF
    0.07
    _________________↵↵
    0.07
    street
    0.07
    OrCreate
    0.07
    mates
    0.07
    Activations Density 0.018%

    No Known Activations