© 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. 106585
    Prev
    Next
    INDEX
    Explanations

    references to animal interactions in a park or safari setting

    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
    çĭĹ
    -0.07
    andest
    -0.07
    incer
    -0.06
    Dog
    -0.06
     Hum
    -0.06
    asu
    -0.06
     dog
    -0.06
    LayoutConstraint
    -0.06
     tuner
    -0.06
     hamstring
    -0.06
    POSITIVE LOGITS
     exhibit
    0.07
     exhib
    0.07
     cyc
    0.07
    edin
    0.06
     specimens
    0.06
    пов
    0.06
     Cyc
    0.06
    ephir
    0.06
     pardon
    0.06
     ;č↵
    0.06
    Activations Density 0.010%

    No Known Activations