© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40761
    Prev
    Next
    INDEX
    Explanations

    specific individual names and titles

    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
    İ
    -0.07
    apore
    -0.06
     Bien
    -0.06
    asper
    -0.06
     ìĦ¬
    -0.06
    ottes
    -0.06
    åĬĽçļĦ
    -0.06
    ilis
    -0.06
    ifestyles
    -0.06
    ÑĢави
    -0.06
    POSITIVE LOGITS
     regarding
    0.08
     about
    0.07
    è°Ī
    0.07
    عÙĨ
    0.07
    about
    0.07
     concerning
    0.07
    opensource
    0.07
     despre
    0.07
     impro
    0.07
     vá»ģ
    0.06
    Activations Density 0.022%

    No Known Activations