© 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. 2995
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the name "Till" and variations of the word "tile."

    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
    imei
    -0.08
    locker
    -0.07
    locks
    -0.07
    cheon
    -0.07
    acht
    -0.06
    orners
    -0.06
    emic
    -0.06
    aux
    -0.06
    interop
    -0.06
    zem
    -0.06
    POSITIVE LOGITS
    ahun
    0.08
    apia
    0.07
     bounced
    0.07
    .EventQueue
    0.07
     recently
    0.07
    ikt
    0.07
    ley
    0.06
     Salon
    0.06
     bounce
    0.06
    /un
    0.06
    Activations Density 0.028%

    No Known Activations