© 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. 125727
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical references related to events or entities

    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
    azine
    -0.08
     Grat
    -0.06
    اشت
    -0.06
    rieb
    -0.06
    âĢ¦↵↵
    -0.06
    vez
    -0.06
    alm
    -0.06
    swith
    -0.06
    15
    -0.06
    unca
    -0.06
    POSITIVE LOGITS
    ì§
    0.07
    Deprecated
    0.07
    Operator
    0.07
    -operator
    0.07
    thinkable
    0.07
    usch
    0.07
    fold
    0.06
    Ñģлов
    0.06
     èĭ¥è¦ģ
    0.06
    Ä±ÅŁ
    0.06
    Activations Density 0.079%

    No Known Activations