© 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. 17-LLAMASCOPE-RES-131K
    6. 40161
    Prev
    Next
    INDEX
    Explanations

    instances of conversational transitions and expressions of surprise or emphasis

    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
    addock
    -0.06
    anging
    -0.06
    hint
    -0.06
     Anatomy
    -0.06
    à¸ļà¸Ĺ
    -0.06
    амп
    -0.06
    anca
    -0.06
    iera
    -0.06
     hypoc
    -0.06
    «
    -0.06
    POSITIVE LOGITS
    ovit
    0.07
     Profession
    0.07
    @js
    0.07
    phin
    0.07
     prostitu
    0.06
    isine
    0.06
    +xml
    0.06
    ret
    0.06
    amu
    0.06
    _notifier
    0.06
    Activations Density 0.005%

    No Known Activations