© 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. 1040
    Prev
    Next
    INDEX
    Explanations

    titles and roles associated with executive leadership positions

    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
    addy
    -0.07
    anja
    -0.07
    punk
    -0.07
    ama
    -0.07
    quer
    -0.07
    acre
    -0.07
    atto
    -0.07
    work
    -0.06
    TURE
    -0.06
    brush
    -0.06
    POSITIVE LOGITS
     Hugo
    0.06
    aux
    0.06
     cum
    0.06
     Yan
    0.06
     Mey
    0.06
    489
    0.06
     (%)
    0.06
     Wikimedia
    0.06
    497
    0.06
    elez
    0.06
    Activations Density 0.006%

    No Known Activations