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. 43837
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entity names

    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
    aux
    -0.07
    o
    -0.07
    OPSIS
    -0.06
    олов
    -0.06
    chio
    -0.06
    ozÃŃ
    -0.06
    .dst
    -0.06
    loat
    -0.06
    iyan
    -0.06
     Gh
    -0.06
    POSITIVE LOGITS
    ub
    0.17
    ubl
    0.11
    ubic
    0.11
    UBL
    0.11
    ubo
    0.10
    ubi
    0.10
    udev
    0.10
    ube
    0.09
    ubit
    0.09
    uber
    0.09
    Activations Density 0.003%

    No Known Activations