© 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. 9-LLAMASCOPE-RES-131K
    11. 96248
    Prev
    Next
    INDEX
    Explanations

    specific references to software applications and file types

    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
     Fritz
    -0.06
    ingly
    -0.06
    esco
    -0.06
     Heller
    -0.06
    orer
    -0.06
    egrate
    -0.06
    é¼
    -0.06
     Asians
    -0.06
    oggler
    -0.06
     Hlav
    -0.06
    POSITIVE LOGITS
    è¾°
    0.07
    AREN
    0.07
    ADB
    0.07
    WRAPPER
    0.07
    RowCount
    0.07
    hare
    0.06
    osen
    0.06
    INGTON
    0.06
    lıģın
    0.06
    PACE
    0.06
    Activations Density 0.001%

    No Known Activations