© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127164
    Prev
    Next
    INDEX
    Explanations

    references to legal regulations or formal statutes

    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
    iled
    -0.06
    yl
    -0.06
     affected
    -0.06
    402
    -0.06
    201
    -0.06
    [
    -0.05
     n
    -0.05
     attitude
    -0.05
    *
    -0.05
    199
    -0.05
    POSITIVE LOGITS
    alace
    0.09
     zev
    0.09
    éĺħ读次æķ°
    0.08
    zcze
    0.08
    !=(
    0.07
    mah
    0.07
    izr
    0.07
    ucker
    0.07
    ¶Į
    0.07
    òng
    0.07
    Activations Density 0.002%

    No Known Activations