© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4372
    Prev
    Next
    INDEX
    Explanations

    references to purchasing affordable drugs

    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
    _sy
    -0.06
    ynes
    -0.06
    èĬ³
    -0.05
     possess
    -0.05
    éī
    -0.05
     worth
    -0.05
     precisely
    -0.05
    xE
    -0.05
    ephy
    -0.05
    å¼Ģå¥ĸ
    -0.05
    POSITIVE LOGITS
    åĩĨ
    0.07
     GOODMAN
    0.07
    onta
    0.07
    BuilderFactory
    0.07
    bes
    0.07
     tiener
    0.07
    iom
    0.07
    ij¸
    0.06
    SizeMode
    0.06
    ä¼´
    0.06
    Activations Density 0.011%

    No Known Activations