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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27503
    Prev
    Next
    INDEX
    Explanations

    mentions of people, particularly in the context of interviews or personal stories

    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
    odied
    -0.07
     hlav
    -0.07
    /mit
    -0.07
    959
    -0.07
    εια
    -0.07
    orthand
    -0.07
    åĿĢ
    -0.07
    heed
    -0.07
     огÑĢа
    -0.06
    ifestyles
    -0.06
    POSITIVE LOGITS
     answering
    0.08
    ves
    0.07
    ãĥĭãĥĥãĤ¯
    0.07
     answers
    0.07
     deflect
    0.06
     explaining
    0.06
    éĢļ
    0.06
     briefly
    0.06
    ke
    0.06
    μÏĨ
    0.06
    Activations Density 0.020%

    No Known Activations