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. 44322
    Prev
    Next
    INDEX
    Explanations

    references to age-related statistics and demographics

    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
     
    -0.13
     the
    -0.11
    1
    -0.11
     a
    -0.11
    2
    -0.11
     H
    -0.11
     S
    -0.10
     as
    -0.10
    3
    -0.10
     C
    -0.10
    POSITIVE LOGITS
    /GPL
    0.11
    (çģ«
    0.11
    омен
    0.10
    (æ°´
    0.10
    _reordered
    0.10
    (éĩij
    0.10
    (æľ¨
    0.10
    bulan
    0.10
    removeAttr
    0.10
    DockControl
    0.10
    Activations Density 0.010%

    No Known Activations