© 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. 121184
    Prev
    Next
    INDEX
    Explanations

    sequences of punctuation marks and certain syntactic structures

    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
    esson
    -0.07
    liers
    -0.07
    gap
    -0.07
    vé
    -0.07
    ipt
    -0.07
    lier
    -0.06
    issen
    -0.06
    æĻ®
    -0.06
    -gap
    -0.06
    icensing
    -0.06
    POSITIVE LOGITS
    unk
    0.06
    Äĥm
    0.06
    xbd
    0.06
     Kraj
    0.06
     HAPP
    0.06
    unga
    0.06
    polator
    0.06
    agal
    0.06
    .slim
    0.06
    agy
    0.05
    Activations Density 0.006%

    No Known Activations