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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129600
    Prev
    Next
    INDEX
    Explanations

    elements related to animal behavior and communication

    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
    egend
    -0.06
    erif
    -0.06
     Cors
    -0.06
    orque
    -0.06
     temper
    -0.06
     doub
    -0.06
    abus
    -0.06
    tparam
    -0.06
     spont
    -0.06
     transf
    -0.06
    POSITIVE LOGITS
     Blind
    0.07
    acons
    0.07
     коÑĢм
    0.07
     klin
    0.07
     blinds
    0.07
     blindness
    0.07
    åĹ
    0.07
     Vladim
    0.07
     sniff
    0.07
     ä¿¡
    0.07
    Activations Density 0.004%

    No Known Activations