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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "what" and phrases that inquire about or reflect upon specific situations or conditions

    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
    isen
    -0.08
    usta
    -0.07
    Logical
    -0.07
     Î
    -0.07
    alus
    -0.07
    usty
    -0.07
    eniz
    -0.07
    داÙħ
    -0.07
    Î
    -0.06
    AGO
    -0.06
    POSITIVE LOGITS
     many
    0.06
     Brush
    0.06
     industry
    0.06
     Fare
    0.06
     ing
    0.06
    ród
    0.06
    caler
    0.06
    ãģŁãĤĬ
    0.06
    689
    0.06
    oping
    0.06
    Activations Density 0.009%

    No Known Activations