© 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. 126096
    Prev
    Next
    INDEX
    Explanations

    pronouns that refer to people

    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
    ãģ¡ãĤĥãĤĵ
    -0.07
    oust
    -0.06
    oley
    -0.06
    loquent
    -0.06
    loy
    -0.06
    ogen
    -0.06
    loff
    -0.06
    oux
    -0.06
     Carly
    -0.06
    oco
    -0.06
    POSITIVE LOGITS
     did
    0.09
    éĤ£æł·
    0.09
     predecessors
    0.07
    å¹ķ
    0.07
    926
    0.06
     Barg
    0.06
    previous
    0.06
    did
    0.06
     predecessor
    0.06
    ÏĪη
    0.06
    Activations Density 0.017%

    No Known Activations