© 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. 55696
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating the speaker's perspective

    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
    zos
    -0.08
    OMEM
    -0.07
    못
    -0.07
    Responder
    -0.07
    Když
    -0.06
    ZA
    -0.06
    pdata
    -0.06
    iben
    -0.06
    /goto
    -0.06
    azers
    -0.06
    POSITIVE LOGITS
     any
    0.08
    any
    0.07
     Any
    0.07
    Any
    0.07
     ever
    0.06
     Broker
    0.06
     Bro
    0.06
    -any
    0.06
    (any
    0.06
    agal
    0.06
    Activations Density 0.009%

    No Known Activations