© 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 EvalsExportsinterp-engineNEWAPI 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. 79940
    Prev
    Next
    INDEX
    Explanations

    ecological terms related to migration and species interactions

    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
    Locker
    -0.06
    ellation
    -0.06
    ienia
    -0.06
    holes
    -0.06
    idian
    -0.06
    ç±
    -0.06
    arius
    -0.06
    aho
    -0.06
    umont
    -0.06
    uble
    -0.06
    POSITIVE LOGITS
     migr
    0.10
     passage
    0.09
     migration
    0.09
     flight
    0.09
     Passage
    0.08
     migrant
    0.08
     Migration
    0.08
     migrate
    0.08
     Goose
    0.08
     migrants
    0.07
    Activations Density 0.005%

    No Known Activations