© 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. 75814
    Prev
    Next
    INDEX
    Explanations

    adjectives describing flexibility and quality

    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
    insky
    -0.06
    à¥Ģद
    -0.06
    ixer
    -0.06
    ãĥ¼ãĥĢ
    -0.06
     Farr
    -0.06
    end
    -0.06
    anka
    -0.06
    edral
    -0.06
    ewe
    -0.06
    eed
    -0.06
    POSITIVE LOGITS
    ÑĢаÑħ
    0.07
    qli
    0.07
     Bundy
    0.06
     ekip
    0.06
    é¼»
    0.06
    inati
    0.06
    _prices
    0.06
    IPC
    0.06
    nas
    0.06
    riel
    0.06
    Activations Density 0.001%

    No Known Activations