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. 43380
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    bay
    -0.08
    irit
    -0.06
    Sold
    -0.06
    tees
    -0.06
     crime
    -0.06
    iki
    -0.06
    ĶåĽŀ
    -0.06
    abei
    -0.06
    ucene
    -0.06
     зв
    -0.06
    POSITIVE LOGITS
     either
    0.07
     Ping
    0.07
     Either
    0.07
    lix
    0.06
    Ping
    0.06
    UGC
    0.06
    ãĥ³ãĥĹ
    0.06
    elman
    0.06
    رة
    0.06
    еÑĢп
    0.06
    Activations Density 0.003%

    No Known Activations