© 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. 130305
    Prev
    Next
    INDEX
    Explanations

    references to electrons and their properties

    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
    arde
    -0.07
     undocumented
    -0.07
    oba
    -0.07
    leine
    -0.06
    going
    -0.06
    allen
    -0.06
    gross
    -0.06
    lemn
    -0.06
    oru
    -0.06
    tech
    -0.06
    POSITIVE LOGITS
    ically
    0.11
    icz
    0.07
    -hole
    0.07
    395
    0.06
    otle
    0.06
    pheric
    0.06
    hod
    0.06
    å¨ľ
    0.06
    ician
    0.06
    ounced
    0.06
    Activations Density 0.016%

    No Known Activations