© 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. 78468
    Prev
    Next
    INDEX
    Explanations

    references to regulatory recommendations and action plans

    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
    å´
    -0.08
    lý
    -0.08
    :CGRect
    -0.08
    å®ģ
    -0.07
    elon
    -0.07
    iyel
    -0.07
    寧
    -0.07
    berry
    -0.07
    ffff
    -0.07
    ija
    -0.07
    POSITIVE LOGITS
     implementation
    0.13
     Implementation
    0.12
     Action
    0.11
     action
    0.11
     implement
    0.11
    Implementation
    0.10
     implementations
    0.10
     Implement
    0.10
     IMPLEMENT
    0.10
    implementation
    0.09
    Activations Density 0.019%

    No Known Activations