© 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. 81764
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" and related phrases indicating additional quantity or information

    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
    awah
    -0.07
    elier
    -0.07
    .templates
    -0.06
    quent
    -0.06
    .Syntax
    -0.06
    çĵ
    -0.06
    erti
    -0.06
    umont
    -0.06
    _LT
    -0.06
    /**č↵
    -0.06
    POSITIVE LOGITS
     further
    0.10
     another
    0.09
    another
    0.08
    Further
    0.08
     again
    0.08
     dalÅ¡ÃŃ
    0.08
     åıĪ
    0.08
    uther
    0.07
     Further
    0.07
    Another
    0.07
    Activations Density 0.021%

    No Known Activations