© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    terms related to linguistics and language

    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
    vik
    -0.07
    seg
    -0.07
    HF
    -0.07
    hta
    -0.07
    asso
    -0.06
     composite
    -0.06
    aptor
    -0.06
    .screen
    -0.06
    hs
    -0.06
    grim
    -0.06
    POSITIVE LOGITS
    ering
    0.09
    opher
    0.07
    rove
    0.07
    uest
    0.06
     gust
    0.06
    214
    0.06
    arda
    0.06
     Eng
    0.06
    usting
    0.06
    orer
    0.06
    Activations Density 0.012%

    No Known Activations