© 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. 70954
    Prev
    Next
    INDEX
    Explanations

    references to notable films and their directors

    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
    arf
    -0.07
    ì½ľ
    -0.07
    antry
    -0.07
    ellt
    -0.06
     Readers
    -0.06
    uest
    -0.06
     Oprah
    -0.06
     cancell
    -0.06
    ertext
    -0.06
    RAND
    -0.06
    POSITIVE LOGITS
     Directors
    0.08
     director
    0.08
     distrib
    0.07
     feature
    0.07
     Director
    0.07
     Distribution
    0.07
     directors
    0.07
     distribute
    0.07
     Distrib
    0.07
     crowdfunding
    0.07
    Activations Density 0.059%

    No Known Activations