© 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. 30163
    Prev
    Next
    INDEX
    Explanations

    references to cultural events, performances, or festivals

    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
    ｡
    -0.08
    lander
    -0.08
    .ÎŁ
    -0.08
     Äijiá»ĥn
    -0.08
    ÅĻes
    -0.07
    éĿ
    -0.07
    Ĥ¹
    -0.07
    ëĿ½
    -0.07
    .':
    -0.07
    ':''
    -0.07
    POSITIVE LOGITS
     (
    0.10
    ;
    0.10
     twice
    0.09
    :
    0.08
     for
    0.07
    ãĢįãĢĮ
    0.07
     ;
    0.07
     ();
    0.07
    0.07
     Aston
    0.07
    Activations Density 0.093%

    No Known Activations