© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27611
    Prev
    Next
    INDEX
    Explanations

    expressions of self-identity and self-reference

    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
    morgan
    -0.07
    /REC
    -0.07
    anzeigen
    -0.07
    onder
    -0.07
    irsch
    -0.07
    (æĹ¥
    -0.07
    onde
    -0.07
     itself
    -0.07
    uppercase
    -0.06
     Darling
    -0.06
    POSITIVE LOGITS
     lucky
    0.07
    ãĥĥãĥĦ
    0.07
    enance
    0.06
    zelf
    0.06
     Cout
    0.06
    886
    0.06
    /th
    0.06
    friend
    0.06
    036
    0.06
    -plus
    0.06
    Activations Density 0.005%

    No Known Activations