© 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. 128803
    Prev
    Next
    INDEX
    Explanations

    technical terms related to device operation and control

    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
    Unc
    -0.06
    iyat
    -0.06
     Jak
    -0.06
    ì¶Ķ
    -0.06
    ordion
    -0.06
    _RENDERER
    -0.06
     Phonetic
    -0.06
     courier
    -0.06
    auce
    -0.06
    _HIDE
    -0.06
    POSITIVE LOGITS
     charging
    0.08
     Charging
    0.07
    arge
    0.07
    etail
    0.06
    æľŃ
    0.06
    odes
    0.06
    apesh
    0.06
    åĨĬ
    0.06
    клад
    0.06
    ç¾
    0.06
    Activations Density 0.003%

    No Known Activations