© 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. 103901
    Prev
    Next
    INDEX
    Explanations

    phrases expressing timing or suitability related to events or actions

    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
    TTY
    -0.06
    cke
    -0.06
    arkin
    -0.06
    .addHandler
    -0.06
    Reuse
    -0.06
     Reservation
    -0.05
    -Le
    -0.05
    rey
    -0.05
     strict
    -0.05
    lobals
    -0.05
    POSITIVE LOGITS
     occasion
    0.08
    occasion
    0.08
    _ask
    0.07
     Zwe
    0.07
     باÛĮ
    0.07
    ινÏĮ
    0.07
    .ask
    0.07
    Topics
    0.07
    rog
    0.07
    ÙĪØ¯ÛĮ
    0.07
    Activations Density 0.008%

    No Known Activations