© 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. 73836
    Prev
    Next
    INDEX
    Explanations

    instances of responsibility or acknowledgment in discussions related to various subjects

    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
     therefore
    -0.11
     accordingly
    -0.10
     however
    -0.09
     wiÄĻc
    -0.09
     donc
    -0.09
     indeed
    -0.09
     thus
    -0.09
    inde
    -0.07
     meanwhile
    -0.07
     first
    -0.07
    POSITIVE LOGITS
     also
    0.11
    also
    0.10
    ä¹Łä¸į
    0.09
     également
    0.09
    Also
    0.09
     también
    0.09
     ALSO
    0.08
     também
    0.08
    hiba
    0.08
     cũng
    0.08
    Activations Density 0.104%

    No Known Activations