© 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. 124669
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming-related structures and symbols

    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
    akers
    -0.07
    intl
    -0.07
    inar
    -0.07
    udic
    -0.07
    ied
    -0.07
    Äĥn
    -0.06
    illo
    -0.06
    ivor
    -0.06
    EEP
    -0.06
    ops
    -0.06
    POSITIVE LOGITS
    459
    0.06
     Buf
    0.06
     Gale
    0.06
    ãĤ¹ãĥŀ
    0.06
    readcr
    0.06
    ancellable
    0.06
    ãģļ
    0.05
    ãĤ
    0.05
     chung
    0.05
    deg
    0.05
    Activations Density 0.224%

    No Known Activations