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. 43384
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols that may indicate errors or unusual items in the text

    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
    одÑĭ
    -0.07
    ckett
    -0.06
     Ben
    -0.06
    à¥ĩयर
    -0.06
    airo
    -0.06
    cdb
    -0.06
    odge
    -0.06
     beads
    -0.06
    urgeon
    -0.06
    hausen
    -0.06
    POSITIVE LOGITS
    bal
    0.18
    BAL
    0.12
     bal
    0.12
    ted
    0.12
    -bal
    0.11
    باÙĦ
    0.10
    abal
    0.10
    ub
    0.10
    dam
    0.09
    ball
    0.09
    Activations Density 0.003%

    No Known Activations