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. 44072
    Prev
    Next
    INDEX
    Explanations

    references to data and reports, particularly in relation to statistics and analysis

    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
    оÑĤи
    -0.06
    ursion
    -0.06
    _MetaData
    -0.06
    siniz
    -0.06
    shal
    -0.06
    vas
    -0.06
    ?action
    -0.06
    podob
    -0.06
    andre
    -0.06
    仿
    -0.06
    POSITIVE LOGITS
     exclude
    0.14
     excludes
    0.13
     excluded
    0.12
     capture
    0.11
     Exclude
    0.11
    exclude
    0.10
     om
    0.10
     captures
    0.10
     omit
    0.10
     covers
    0.09
    Activations Density 0.061%

    No Known Activations