© 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. 62846
    Prev
    Next
    INDEX
    Explanations

    references to Australia and discussions about social and environmental issues

    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
     Westbrook
    -0.07
     Lambda
    -0.07
    grass
    -0.07
    çĸ¾
    -0.06
    μι
    -0.06
    loid
    -0.06
    éĿ©åij½
    -0.06
    CTL
    -0.06
    ilda
    -0.06
    лож
    -0.06
    POSITIVE LOGITS
     ourselves
    0.09
     Foreign
    0.07
     Security
    0.07
     foreign
    0.07
     security
    0.06
    ipel
    0.06
    cent
    0.06
    Secure
    0.06
    jos
    0.06
    ellas
    0.06
    Activations Density 0.003%

    No Known Activations