© 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. 127411
    Prev
    Next
    INDEX
    Explanations

    specific references to literary analysis and textual interpretation

    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
     Philosoph
    -0.07
    argo
    -0.06
     Craw
    -0.06
     ROCK
    -0.06
    longleftrightarrow
    -0.06
    lever
    -0.06
    occo
    -0.06
    zas
    -0.06
     EURO
    -0.06
    FO
    -0.05
    POSITIVE LOGITS
     Blasio
    0.07
    sing
    0.07
    sert
    0.07
    auer
    0.07
    ãĥĶãĥ¼
    0.07
    DMI
    0.06
    acre
    0.06
    apest
    0.06
    iti
    0.06
    URAL
    0.06
    Activations Density 0.006%

    No Known Activations