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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 95999
    Prev
    Next
    INDEX
    Explanations

    personal pronouns in the text

    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
    lete
    -0.07
    èģĺ
    -0.07
    {}_
    -0.06
    ovit
    -0.06
    اÙĤÙĦ
    -0.06
    alsex
    -0.06
    lite
    -0.06
    .utilities
    -0.06
    LOUD
    -0.06
    irts
    -0.06
    POSITIVE LOGITS
    857
    0.07
     opp
    0.07
    eso
    0.07
    rganization
    0.07
     pert
    0.06
     neutr
    0.06
    cert
    0.06
    iver
    0.06
    uator
    0.06
    ough
    0.06
    Activations Density 0.036%

    No Known Activations