© 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. 130867
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that convey quality and appeal

    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
    ables
    -0.08
    ubbo
    -0.08
    asin
    -0.07
    AMED
    -0.07
    ÄĽtÅ¡
    -0.07
    uki
    -0.07
    emarks
    -0.07
    èĨ
    -0.06
    round
    -0.06
    ungi
    -0.06
    POSITIVE LOGITS
     enough
    0.09
    pta
    0.06
    odynam
    0.06
    ÏĢά
    0.06
    ival
    0.06
    oard
    0.06
     zwar
    0.06
    úi
    0.06
    ippet
    0.06
    implify
    0.06
    Activations Density 0.046%

    No Known Activations