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. 43934
    Prev
    Next
    INDEX
    Explanations

    terms related to racism and racial issues

    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
    erde
    -0.07
    ynamo
    -0.06
    hart
    -0.06
    irth
    -0.06
    hg
    -0.06
    ador
    -0.06
    endor
    -0.06
    ",__
    -0.06
    å¥ī
    -0.06
    adora
    -0.06
    POSITIVE LOGITS
    ially
    0.13
    ism
    0.12
    ists
    0.11
    IALIZED
    0.11
    ist
    0.11
    aille
    0.10
    ailles
    0.10
    quet
    0.10
    ISM
    0.10
    isms
    0.09
    Activations Density 0.005%

    No Known Activations