© 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. 74370
    Prev
    Next
    INDEX
    Explanations

    references to personal narratives and self-disclosure

    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
    è«
    -0.07
    uc
    -0.06
    forth
    -0.06
    iks
    -0.06
    leck
    -0.06
    isse
    -0.06
     chances
    -0.06
     Lect
    -0.06
    dn
    -0.06
    uÄį
    -0.06
    POSITIVE LOGITS
     about
    0.09
    about
    0.09
     history
    0.09
     background
    0.08
    /stdc
    0.07
    /about
    0.07
     tentang
    0.07
    history
    0.07
     yourselves
    0.07
     ourselves
    0.06
    Activations Density 0.006%

    No Known Activations