© 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. 72525
    Prev
    Next
    INDEX
    Explanations

    usage of apostrophes, particularly in contractions and possessives

    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
    umatic
    -0.09
    aurant
    -0.07
    FAULT
    -0.07
    lse
    -0.07
     NotImplemented
    -0.07
    _accessor
    -0.07
    uC
    -0.06
    ãģĸ
    -0.06
    égor
    -0.06
    ÙĨØ©
    -0.06
    POSITIVE LOGITS
    vez
    0.07
    ạn
    0.06
    ness
    0.06
    aber
    0.06
    ĺIJ
    0.06
    ç·¨
    0.06
    ham
    0.06
    akens
    0.06
    ha
    0.06
    aten
    0.06
    Activations Density 0.002%

    No Known Activations