© 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. 29008
    Prev
    Next
    INDEX
    Explanations

    references to specific shows and their content

    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
    ÚĨÙĩ
    -0.07
     Lup
    -0.07
    gett
    -0.07
    Å¡Å¥
    -0.07
    okt
    -0.07
    dit
    -0.07
    ]=>
    -0.07
    ught
    -0.07
    _prefs
    -0.07
    unta
    -0.07
    POSITIVE LOGITS
    ieg
    0.07
    ebek
    0.06
    ikut
    0.06
    رÙĩ
    0.05
    osc
    0.05
    ri
    0.05
    adj
    0.05
     Os
    0.05
     [#
    0.05
    676
    0.05
    Activations Density 0.024%

    No Known Activations