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

    Neuronpedia

    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. 127168
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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
    ç§ĭ
    -0.07
     meas
    -0.07
    er
    -0.07
    .isDefined
    -0.06
    .GroupLayout
    -0.06
    ìļ´ëį°
    -0.06
     trÃŃ
    -0.06
     prospect
    -0.06
    quip
    -0.06
    lsen
    -0.06
    POSITIVE LOGITS
    201
    0.07
    PHA
    0.07
    864
    0.07
    OTES
    0.07
    ousand
    0.06
    Û²Û°Û±
    0.06
    ÙĪاء
    0.06
    OfType
    0.06
    egr
    0.06
    ought
    0.06
    Activations Density 0.009%

    No Known Activations