© 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. 94135
    Prev
    Next
    INDEX
    Explanations

    medical treatments and their related conditions

    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
     inval
    -0.08
    yal
    -0.07
    _DIP
    -0.07
    steen
    -0.06
     Ampl
    -0.06
     exem
    -0.06
    AMPL
    -0.06
    매
    -0.06
    738
    -0.06
     Ngá»įc
    -0.06
    POSITIVE LOGITS
    ายà¸Ļ
    0.07
     help
    0.07
    ora
    0.06
    athe
    0.06
    odia
    0.06
    (help
    0.06
    help
    0.06
     Lives
    0.06
    FORCE
    0.06
    frei
    0.06
    Activations Density 0.021%

    No Known Activations