© 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. 15-LLAMASCOPE-RES-131K
    11. 87706
    Prev
    Next
    INDEX
    Explanations

    negative prefixes or indicators

    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
    ulus
    -0.07
    abar
    -0.07
    abol
    -0.07
    eland
    -0.06
     Abram
    -0.06
    apat
    -0.06
    ema
    -0.06
    ym
    -0.06
    kowski
    -0.06
    abel
    -0.06
    POSITIVE LOGITS
    sou
    0.07
    /by
    0.06
    orian
    0.06
    psc
    0.06
     ÙħÙĨÙĩ
    0.06
    oram
    0.06
    clc
    0.06
     Mec
    0.06
     Sanat
    0.06
     Luz
    0.06
    Activations Density 0.004%

    No Known Activations