© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3720
    Prev
    Next
    INDEX
    Explanations

    mentions of dogs

    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
    æ¦ľ
    -0.07
    egie
    -0.07
    .timing
    -0.07
    _DAC
    -0.07
     kitt
    -0.07
    fad
    -0.07
    conda
    -0.07
    iero
    -0.07
     Painter
    -0.07
    OfType
    -0.06
    POSITIVE LOGITS
    friendly
    0.08
     Friendly
    0.08
     whisper
    0.08
    gie
    0.08
    gy
    0.08
     friendly
    0.08
     Whisper
    0.07
     owners
    0.07
    -friendly
    0.07
    ole
    0.07
    Activations Density 0.006%

    No Known Activations