© 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. 127843
    Prev
    Next
    INDEX
    Explanations

    reported speech or statements in the text

    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
    thal
    -0.07
    ZO
    -0.07
    ish
    -0.07
    idade
    -0.07
    oft
    -0.06
     Howe
    -0.06
    ise
    -0.06
    zeit
    -0.06
    ène
    -0.06
    itis
    -0.06
    POSITIVE LOGITS
    addtogroup
    0.08
    lobals
    0.07
    /is
    0.07
    ugins
    0.07
    Ñĩенко
    0.07
    ÄĮesk
    0.07
    ugin
    0.07
    ombat
    0.07
     con
    0.06
    ://%
    0.06
    Activations Density 0.003%

    No Known Activations