© 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. 59903
    Prev
    Next
    INDEX
    Explanations

    the phrase "according to."

    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
    aub
    -0.08
    linger
    -0.07
    622
    -0.06
    моÑĢ
    -0.06
    ingen
    -0.06
     decentral
    -0.06
    sec
    -0.06
    ummings
    -0.06
    odynamics
    -0.06
    zie
    -0.06
    POSITIVE LOGITS
    æ£ĭ
    0.06
     Kens
    0.06
    care
    0.06
    /svg
    0.06
     Baths
    0.06
    getOrElse
    0.06
     INLINE
    0.06
    coat
    0.06
    .ParseException
    0.06
    اÙĨس
    0.06
    Activations Density 0.001%

    No Known Activations