© 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. 15-LLAMASCOPE-RES-131K
    11. 27073
    Prev
    Next
    INDEX
    Explanations

    philosophical questions and discussions about identity

    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
    618
    -0.06
    @show
    -0.06
    illin
    -0.06
    Äįi
    -0.06
     IonicPage
    -0.06
    YD
    -0.06
    Ãłng
    -0.06
    achi
    -0.06
    òi
    -0.06
    cki
    -0.06
    POSITIVE LOGITS
    SystemService
    0.06
    ucch
    0.06
    lod
    0.06
     Erotische
    0.06
     erót
    0.06
     Statue
    0.06
    oter
    0.06
    uluk
    0.06
    Wis
    0.06
     itself
    0.06
    Activations Density 0.002%

    No Known Activations