© 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. 118996
    Prev
    Next
    INDEX
    Explanations

    themes related to narratives and storytelling devices

    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
    quam
    -0.07
    бÑĥдÑĮ
    -0.07
    rick
    -0.06
     Malone
    -0.06
    âĢ²
    -0.06
    sse
    -0.06
    /drivers
    -0.06
    коÑĢиÑģÑĤ
    -0.06
    erdem
    -0.06
    ud
    -0.06
    POSITIVE LOGITS
     others
    0.09
     etc
    0.07
    918
    0.07
    ãģªãģ©
    0.06
     newText
    0.06
     sometimes
    0.06
     certain
    0.06
    ãĥĥãĥģ
    0.06
    ofs
    0.06
     other
    0.06
    Activations Density 0.038%

    No Known Activations