© 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 EvalsExportsAPI 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. 85709
    Prev
    Next
    INDEX
    Explanations

    references to subjects and topics within a text

    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
     topic
    -0.10
    -topic
    -0.09
    matter
    -0.09
     topics
    -0.09
    angs
    -0.08
     subject
    -0.08
     subjects
    -0.08
    Topic
    -0.08
    /topic
    -0.08
     Topic
    -0.07
    POSITIVE LOGITS
    èo
    0.07
    otle
    0.07
    chin
    0.07
     mech
    0.06
    наÑĢ
    0.06
    ernaut
    0.06
    less
    0.06
    ÑĪин
    0.06
    _drvdata
    0.06
    ChangeEvent
    0.06
    Activations Density 0.008%

    No Known Activations