© 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 EvalsExportsinterp-engineNEWAPI 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. 27372
    Prev
    Next
    INDEX
    Explanations

    references to literature and academic qualifications

    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
    reur
    -0.07
    omes
    -0.07
    rement
    -0.07
    retch
    -0.07
    laus
    -0.07
    ailles
    -0.06
    Accessory
    -0.06
     Kend
    -0.06
    éĻ
    -0.06
    ehler
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸ª
    0.06
    ervices
    0.06
     Nová
    0.06
    ylum
    0.06
    ÑĢей
    0.06
     strength
    0.05
    庫
    0.05
    _gui
    0.05
    AMPLE
    0.05
    end
    0.05
    Activations Density 0.000%

    No Known Activations