© 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 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. 87514
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence endings

    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
    regon
    -0.07
    akk
    -0.07
    woff
    -0.07
    -transitional
    -0.06
    owell
    -0.06
    oice
    -0.06
    orris
    -0.06
    wolf
    -0.06
    cis
    -0.06
    kaar
    -0.06
    POSITIVE LOGITS
    679
    0.06
    739
    0.06
     ring
    0.06
    715
    0.06
    -under
    0.05
     Amb
    0.05
    urate
    0.05
    ãĥ©ãĥ³
    0.05
     emp
    0.05
    _under
    0.05
    Activations Density 0.000%

    No Known Activations