© 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. 77813
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Sandra."

    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
    oda
    -0.08
    ister
    -0.08
    ster
    -0.07
    inn
    -0.07
    iling
    -0.06
    ¯u
    -0.06
    reno
    -0.06
    ovu
    -0.06
    emax
    -0.06
    etty
    -0.06
    POSITIVE LOGITS
    upported
    0.07
    ussen
    0.06
    een
    0.06
    vik
    0.06
    alth
    0.06
     Buffered
    0.06
    wich
    0.06
    akan
    0.06
    agma
    0.06
     Consent
    0.06
    Activations Density 0.003%

    No Known Activations