© 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. 56371
    Prev
    Next
    INDEX
    Explanations

    topics related to role-playing games and associated genres

    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
    enga
    -0.09
    asti
    -0.08
    [__
    -0.07
    ãģ¼
    -0.07
    ãģĸ
    -0.07
    arsi
    -0.07
    insi
    -0.07
    uzzi
    -0.07
    irim
    -0.07
    wyn
    -0.07
    POSITIVE LOGITS
     nor
    0.17
     anymore
    0.16
     necessarily
    0.12
     or
    0.11
    nor
    0.10
     directly
    0.10
     sondern
    0.10
    Nor
    0.10
     Nor
    0.09
     بÙĦÚ©Ùĩ
    0.09
    Activations Density 0.041%

    No Known Activations