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. 44368
    Prev
    Next
    INDEX
    Explanations

    phrases and references to locations or points of inquiry

    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
    them
    -0.07
    nya
    -0.07
    åĺĽ
    -0.06
     tidak
    -0.06
    scan
    -0.06
    uisse
    -0.06
     eux
    -0.06
    ly
    -0.06
    دارÛĮ
    -0.06
    pler
    -0.06
    POSITIVE LOGITS
    /how
    0.19
     else
    0.18
     exactly
    0.17
    abouts
    0.17
     they
    0.15
    upon
    0.15
    /if
    0.15
    fore
    0.15
    ever
    0.14
     we
    0.13
    Activations Density 0.029%

    No Known Activations