© 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. 129790
    Prev
    Next
    INDEX
    Explanations

    phrases indicating novelty or updates

    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
    oids
    -0.06
     Essex
    -0.06
    esp
    -0.06
    igue
    -0.06
     Gerard
    -0.06
    oft
    -0.06
    itler
    -0.06
    기ìĹħ
    -0.06
    å¼¾
    -0.06
    bul
    -0.06
    POSITIVE LOGITS
     design
    0.06
    ache
    0.06
    ilton
    0.06
    #aa
    0.06
    factor
    0.06
    mainwindow
    0.06
    illet
    0.06
    _INITIALIZ
    0.06
    renders
    0.06
    коÑĢ
    0.06
    Activations Density 0.000%

    No Known Activations