© 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. 4567
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives indicating emotional depth or beauty

    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
    istically
    -0.07
     Bulk
    -0.07
    uously
    -0.06
    ìłģìľ¼ë¡ľ
    -0.06
     Cou
    -0.06
    lier
    -0.06
    aneously
    -0.06
    åľ¨çº¿è§Ĥçľĭ
    -0.06
    lessly
    -0.06
    103
    -0.06
    POSITIVE LOGITS
    enco
    0.08
    uthor
    0.07
    ascar
    0.07
    -config
    0.07
    uencia
    0.06
    sgiving
    0.06
    iggers
    0.06
    quirer
    0.06
    ais
    0.06
    olls
    0.06
    Activations Density 0.038%

    No Known Activations