© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94111
    Prev
    Next
    INDEX
    Explanations

    references to scientific methods and measurements

    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
    operands
    -0.07
    جÙĪ
    -0.07
    asad
    -0.07
     dna
    -0.07
    antom
    -0.07
    /trunk
    -0.07
    resolver
    -0.07
    cko
    -0.07
    DNA
    -0.07
     ãħ¡
    -0.07
    POSITIVE LOGITS
     Shay
    0.06
    icens
    0.05
     Billy
    0.05
     Rat
    0.05
     Urb
    0.05
    358
    0.05
    tool
    0.05
    Billy
    0.05
     rose
    0.05
    rito
    0.05
    Activations Density 0.001%

    No Known Activations