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. 43742
    Prev
    Next
    INDEX
    Explanations

    various Unicode characters, including those related to formatting or encoding

    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
    alach
    -0.07
    ặng
    -0.06
    YST
    -0.06
    ovÃŃ
    -0.06
    ثار
    -0.06
    è¢ĭ
    -0.06
    reece
    -0.06
     fundraising
    -0.06
     dispatch
    -0.06
     Wikispecies
    -0.06
    POSITIVE LOGITS
     rent
    0.12
     renters
    0.12
     lease
    0.12
     renting
    0.12
    Rent
    0.12
     Rent
    0.12
     rents
    0.11
     rental
    0.11
     landlord
    0.11
     landlords
    0.11
    Activations Density 0.006%

    No Known Activations