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. 5425
    Prev
    Next
    INDEX
    Explanations

    instances of characters on a journey or exploration

    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
     FindObjectOfType
    -0.07
    ITA
    -0.06
    'gc
    -0.06
    ActionCreators
    -0.06
    еви
    -0.06
     Mond
    -0.06
    igy
    -0.06
    ETA
    -0.06
    rief
    -0.06
     !"
    -0.06
    POSITIVE LOGITS
    strup
    0.09
    abras
    0.07
     okay
    0.06
    errer
    0.06
    ucch
    0.06
    íķľíħĮ
    0.06
     lub
    0.06
    fs
    0.06
    iff
    0.06
    adin
    0.06
    Activations Density 0.000%

    No Known Activations