© 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. 80312
    Prev
    Next
    INDEX
    Explanations

    instances of the word "too" indicating excessiveness or overindulgence

    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
    avou
    -0.06
     Bij
    -0.06
    enet
    -0.06
    compat
    -0.06
     crossorigin
    -0.06
    shi
    -0.06
    .Requires
    -0.06
    setEnabled
    -0.06
    heets
    -0.06
    ÛĢ
    -0.06
    POSITIVE LOGITS
     much
    0.08
    Much
    0.08
    much
    0.08
     Much
    0.08
    aked
    0.07
    ething
    0.07
     far
    0.07
     MUCH
    0.06
    aucoup
    0.06
    saida
    0.06
    Activations Density 0.019%

    No Known Activations