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. 44425
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and notations

    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
    ål
    -0.06
    achu
    -0.06
     Asc
    -0.06
    wis
    -0.06
    ohana
    -0.06
    etsy
    -0.06
    odesk
    -0.06
    éry
    -0.06
    arme
    -0.06
    iropr
    -0.06
    POSITIVE LOGITS
    non
    0.13
    newline
    0.11
    cr
    0.11
    label
    0.10
    hs
    0.10
    med
    0.10
    phant
    0.09
    nop
    0.09
    \\
    0.09
    \\"
    0.09
    Activations Density 0.259%

    No Known Activations