Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93842
    Prev
    Next
    INDEX
    Explanations

    references to social issues and community support

    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
    ЯкÑīо
    -0.07
    ÐłÐ¾Ð·
    -0.07
    Як
    -0.07
    obec
    -0.07
    Це
    -0.07
    ório
    -0.07
    วà¸Ļ
    -0.07
    éro
    -0.07
     migrationBuilder
    -0.07
    окÑĢем
    -0.07
    POSITIVE LOGITS
     McCart
    0.07
    .
    0.06
     Niet
    0.06
    ln
    0.06
    ëŀįëĭĪëĭ¤
    0.06
     Tuy
    0.06
    åĩ½
    0.05
    ")!=
    0.05
    İ
    0.05
    оÑīи
    0.05
    Activations Density 0.134%

    No Known Activations