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. 29190
    Prev
    Next
    INDEX
    Explanations

    conditional statements and questions related to obligations or scenarios

    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
     Phaser
    -0.08
    ÑĢави
    -0.07
    arte
    -0.07
    رÛĮÙģ
    -0.07
    phas
    -0.07
    onde
    -0.07
     акÑĤÑĥ
    -0.06
    γκα
    -0.06
    orer
    -0.06
    raw
    -0.06
    POSITIVE LOGITS
    965
    0.08
    annes
    0.07
     exceeds
    0.07
     demonstr
    0.06
     exceed
    0.06
    maal
    0.06
    unch
    0.06
    uzz
    0.06
     subsequently
    0.06
    ivities
    0.06
    Activations Density 0.021%

    No Known Activations