© 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. 54844
    Prev
    Next
    INDEX
    Explanations

    conjunctions and numerical data related to change or comparison

    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
    éł
    -0.08
    fdc
    -0.07
    ÙıÙĨ
    -0.07
    ãģ«ãģĹãģ¦
    -0.07
    é¼
    -0.07
    alion
    -0.07
    dbc
    -0.07
    иÑģÑĤÑĢа
    -0.06
    ÑĢоÑİ
    -0.06
     Ank
    -0.06
    POSITIVE LOGITS
    aint
    0.06
    ãĤī
    0.06
     Goldberg
    0.06
    0.06
    isch
    0.06
    cr
    0.06
    ire
    0.06
    udies
    0.05
    76
    0.05
     surtout
    0.05
    Activations Density 0.015%

    No Known Activations