© 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. 82946
    Prev
    Next
    INDEX
    Explanations

    measurements related to inches and their various expressions

    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
    ument
    -0.08
    ucci
    -0.08
    æĢ§çļĦ
    -0.08
    entar
    -0.07
    oeff
    -0.07
    aran
    -0.07
    /MPL
    -0.07
    ellen
    -0.07
    ARGIN
    -0.07
    Ñīик
    -0.07
    POSITIVE LOGITS
    -long
    0.11
    -wide
    0.09
    (es
    0.08
    es
    0.08
    iesta
    0.08
    Rule
    0.07
    maid
    0.07
    long
    0.07
    rule
    0.07
    bread
    0.07
    Activations Density 0.011%

    No Known Activations