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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5289
    Prev
    Next
    INDEX
    Explanations

    references to blogs and blogging

    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
    ãĤ¶ãĥ¼
    -0.08
    alcon
    -0.07
    deen
    -0.07
    elease
    -0.07
    ebin
    -0.07
    ÑģпÑĸлÑĮ
    -0.07
    enko
    -0.07
    znik
    -0.07
    ëĦIJ
    -0.07
     gratuites
    -0.07
    POSITIVE LOGITS
    gers
    0.14
    ging
    0.12
    ged
    0.10
    gs
    0.10
    spot
    0.09
    gy
    0.08
    gings
    0.08
    her
    0.08
    roll
    0.08
    gin
    0.08
    Activations Density 0.006%

    No Known Activations