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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71551
    Prev
    Next
    INDEX
    Explanations

    mentions of the "Lord of the Rings" series and its related content

    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
    ikt
    -0.07
    abel
    -0.07
    dit
    -0.06
    ulla
    -0.06
     branch
    -0.06
    hey
    -0.06
    overs
    -0.06
    ajo
    -0.06
    ida
    -0.06
    ald
    -0.06
    POSITIVE LOGITS
    esses
    0.07
    ApplicationBuilder
    0.07
    tega
    0.07
    .asc
    0.07
     INTERRUPTION
    0.07
    buie
    0.06
    ocache
    0.06
    anship
    0.06
    rá
    0.06
    ormsg
    0.06
    Activations Density 0.003%

    No Known Activations