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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84206
    Prev
    Next
    INDEX
    Explanations

    mentions of the Drosophila organism and its genetic elements

    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
     minded
    -0.07
    licit
    -0.06
     Rails
    -0.06
     Cyr
    -0.06
    kus
    -0.06
    uracy
    -0.06
    .scalar
    -0.06
    OUNDS
    -0.06
    ilib
    -0.06
    iglia
    -0.06
    POSITIVE LOGITS
    olate
    0.07
    _suspend
    0.07
    Susp
    0.07
     susp
    0.07
     suspension
    0.06
     Cumhuriyeti
    0.06
    :::::
    0.06
     embryos
    0.06
    /java
    0.06
    -human
    0.06
    Activations Density 0.032%

    No Known Activations