© 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. 9-LLAMASCOPE-RES-131K
    11. 97557
    Prev
    Next
    INDEX
    Explanations

    strategic military plans and operations

    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
    ebek
    -0.07
    avel
    -0.06
    amak
    -0.06
     पह
    -0.06
    ogle
    -0.06
    rschein
    -0.06
    ruba
    -0.06
    ernet
    -0.06
    veillance
    -0.06
    amet
    -0.06
    POSITIVE LOGITS
    Ä°ÅŁ
    0.07
    ÃŃk
    0.06
     pré
    0.06
     voks
    0.06
    ÑģÑĤиÑĩ
    0.06
    Implicit
    0.06
    iest
    0.06
    ÏĦÎŃ
    0.06
    _defaults
    0.06
    lett
    0.06
    Activations Density 0.033%

    No Known Activations