© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90209
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and community engagement across various locations

    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
    endar
    -0.08
    anvas
    -0.07
    venta
    -0.07
    avan
    -0.07
    ouz
    -0.07
    еÑĢÑĤа
    -0.06
    pla
    -0.06
    lsi
    -0.06
    á»iji
    -0.06
    mie
    -0.06
    POSITIVE LOGITS
     throughout
    0.11
     everywhere
    0.11
     worldwide
    0.10
     across
    0.10
    éģį
    0.08
     Throughout
    0.08
     Across
    0.07
    Throughout
    0.07
     nationwide
    0.07
     globe
    0.07
    Activations Density 0.054%

    No Known Activations