© 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. 59165
    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
    porter
    -0.07
    illas
    -0.06
     Seen
    -0.06
    orra
    -0.06
    ůj
    -0.06
    extension
    -0.06
    Dispatch
    -0.06
    urv
    -0.06
     ||=
    -0.06
    ÑĽ
    -0.06
    POSITIVE LOGITS
    eka
    0.08
     writ
    0.06
    rying
    0.06
    agan
    0.06
    rieving
    0.06
    360
    0.06
     Franken
    0.06
    ibase
    0.06
    odka
    0.06
    nth
    0.06
    Activations Density 0.000%

    No Known Activations