© 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. 126964
    Prev
    Next
    INDEX
    Explanations

    comparisons and analogies

    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
    illac
    -0.07
    eker
    -0.07
    riott
    -0.06
     Nic
    -0.06
    anim
    -0.06
    igue
    -0.06
    ¼åIJĪ
    -0.06
    ilo
    -0.06
    æīĢ
    -0.06
    iw
    -0.06
    POSITIVE LOGITS
     someone
    0.07
    would
    0.06
     asking
    0.06
    vida
    0.06
    íķĺëĭ¤
    0.06
    someone
    0.06
     similarly
    0.06
     Someone
    0.06
     would
    0.06
    ÌĨ
    0.06
    Activations Density 0.011%

    No Known Activations