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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43661
    Prev
    Next
    INDEX
    Explanations

    specific characters and symbols that could represent encoding issues or data corruption

    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
    blick
    -0.07
    ÏĥÏĨ
    -0.07
    áÄį
    -0.07
     inspector
    -0.06
    oland
    -0.06
    /Graphics
    -0.06
    _HERSHEY
    -0.06
     عÙĤ
    -0.06
     insured
    -0.06
    éīĦ
    -0.06
    POSITIVE LOGITS
     harvesting
    0.15
     harvest
    0.15
     harvested
    0.14
     Harvest
    0.13
     har
    0.12
     powering
    0.12
     energy
    0.11
     power
    0.11
     scav
    0.10
     charging
    0.10
    Activations Density 0.007%

    No Known Activations