© 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. 15-LLAMASCOPE-RES-131K
    11. 88142
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related structural elements in sentences

    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
    azu
    -0.07
    еком
    -0.07
    phere
    -0.07
     DisplayName
    -0.07
    Moon
    -0.07
    isque
    -0.07
    ارÙģ
    -0.06
     Moon
    -0.06
     Primitive
    -0.06
    _PD
    -0.06
    POSITIVE LOGITS
    ±
    0.07
    tember
    0.07
    dit
    0.06
    roker
    0.06
    ilate
    0.06
     Tang
    0.06
     likewise
    0.06
    ones
    0.06
    odzi
    0.06
    ents
    0.06
    Activations Density 0.015%

    No Known Activations