Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71332
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical constructs in programming or data structures

    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
    zsche
    -0.08
    astle
    -0.07
    ngth
    -0.07
     dopl
    -0.06
    isoft
    -0.06
     TERMS
    -0.06
    elman
    -0.06
    _nonce
    -0.06
    phan
    -0.06
    ().'/
    -0.06
    POSITIVE LOGITS
     three
    0.09
     third
    0.08
    three
    0.07
     second
    0.07
    3
    0.07
    âij¢
    0.07
     two
    0.06
    ä¸ī个
    0.06
    third
    0.06
     five
    0.06
    Activations Density 0.042%

    No Known Activations