© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 126086
    Prev
    Next
    INDEX
    Explanations

    discussions related to criticism of artistic adaptations

    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
    ylko
    -0.08
     Zuk
    -0.07
    oyal
    -0.07
     welche
    -0.07
    ennen
    -0.07
    ennai
    -0.07
    illa
    -0.07
    enna
    -0.07
     whom
    -0.07
     eskort
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĤº
    0.07
    Tween
    0.07
    nid
    0.06
    кан
    0.06
    vecs
    0.06
    eri
    0.06
    ắm
    0.06
    sis
    0.06
    Äįet
    0.06
    ...č↵
    0.06
    Activations Density 0.090%

    No Known Activations