© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94361
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and periods indicating the end of sentences

    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
     caval
    -0.07
    ultz
    -0.07
    owski
    -0.07
    ÙĬز
    -0.07
    rado
    -0.06
     cez
    -0.06
     accord
    -0.06
    /upload
    -0.06
    eness
    -0.06
    adh
    -0.06
    POSITIVE LOGITS
     bod
    0.06
    anford
    0.06
    olen
    0.06
    kul
    0.06
    DX
    0.06
     пÑĢоп
    0.06
    öy
    0.06
    óż
    0.06
    QL
    0.06
    vil
    0.06
    Activations Density 0.006%

    No Known Activations