© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129524
    Prev
    Next
    INDEX
    Explanations

    references to documents or records with specific dates and editions

    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
    evin
    -0.07
    alan
    -0.06
    atches
    -0.06
    инÑĭ
    -0.06
    ãģıãĤī
    -0.06
    op
    -0.06
    ÑĢÑĥн
    -0.06
    ague
    -0.05
    ants
    -0.05
    apt
    -0.05
    POSITIVE LOGITS
    ERSION
    0.08
    DATED
    0.08
     semiclass
    0.08
     latest
    0.07
     update
    0.07
    URRED
    0.07
     updated
    0.07
    .updateDynamic
    0.07
    -update
    0.07
    (updated
    0.07
    Activations Density 0.035%

    No Known Activations