© 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. 119086
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to counts or increments related to data transmission and error handling

    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
    bilder
    -0.07
     createState
    -0.07
    ieux
    -0.07
     bufio
    -0.07
     batches
    -0.06
    uite
    -0.06
    ogn
    -0.06
    éĵº
    -0.06
    bcm
    -0.06
    jak
    -0.06
    POSITIVE LOGITS
     count
    0.13
     counts
    0.11
    count
    0.11
     counted
    0.11
     COUNT
    0.10
     increment
    0.10
    .increment
    0.10
     Count
    0.10
    .count
    0.10
     incremented
    0.10
    Activations Density 0.064%

    No Known Activations