© 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. 3685
    Prev
    Next
    INDEX
    Explanations

    references to animal breeds and their characteristics

    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
    udent
    -0.08
    etter
    -0.07
    ût
    -0.07
    ynchronously
    -0.07
    еж
    -0.07
    Shell
    -0.06
    istrat
    -0.06
    hawk
    -0.06
    ueil
    -0.06
    -setup
    -0.06
    POSITIVE LOGITS
     breed
    0.07
     Pie
    0.07
     genetic
    0.06
    morph
    0.06
    bred
    0.06
     crosses
    0.06
     stud
    0.06
     pie
    0.06
     descent
    0.06
     Pend
    0.06
    Activations Density 0.026%

    No Known Activations