© 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. 119430
    Prev
    Next
    INDEX
    Explanations

    phrases or terms indicating sources or origins

    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
     itself
    -0.07
    gregator
    -0.07
    á»IJ
    -0.07
    οÏĤ
    -0.06
     gratuites
    -0.06
    ekil
    -0.06
    iers
    -0.06
    antar
    -0.06
    ัศ
    -0.06
    баÑĩ
    -0.06
    POSITIVE LOGITS
     among
    0.10
     amongst
    0.09
    among
    0.09
     Among
    0.07
     several
    0.07
     options
    0.07
    enville
    0.07
    arro
    0.07
    Among
    0.07
    options
    0.07
    Activations Density 0.003%

    No Known Activations