© 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. 108280
    Prev
    Next
    INDEX
    Explanations

    mentions of stray dogs and related situations involving their care and management

    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
    é¡¿
    -0.07
    sov
    -0.07
     terminator
    -0.06
    ToBounds
    -0.06
     впеÑĢед
    -0.06
    ç¦ģ
    -0.06
    adam
    -0.06
    egend
    -0.06
    endez
    -0.06
    éļĽ
    -0.06
    POSITIVE LOGITS
    åĤ¬
    0.08
    arta
    0.07
     waited
    0.07
    defaults
    0.07
     failing
    0.07
     defaulted
    0.07
     default
    0.07
     automatically
    0.07
     fails
    0.07
     patience
    0.06
    Activations Density 0.043%

    No Known Activations