© 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. 17-LLAMASCOPE-RES-131K
    11. 60607
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate product condition and guarantees

    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
     Distrib
    -0.07
    trace
    -0.07
    version
    -0.06
     hạng
    -0.06
    .touches
    -0.06
    iot
    -0.06
    umper
    -0.06
    .constructor
    -0.06
    ειÏĤ
    -0.06
    äºĭåĭĻ
    -0.06
    POSITIVE LOGITS
     description
    0.08
    ViewItem
    0.08
     bidder
    0.07
    -description
    0.07
     item
    0.07
    itle
    0.07
     descriptions
    0.07
     age
    0.07
     condition
    0.07
     describe
    0.07
    Activations Density 0.005%

    No Known Activations