© 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. 123728
    Prev
    Next
    INDEX
    Explanations

    mentions of "Johns Hopkins" and related phrases

    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
    itious
    -0.09
    }elseif
    -0.08
    ADIO
    -0.07
    .raises
    -0.07
    OUS
    -0.07
    à¸ģาร
    -0.07
    okoj
    -0.07
    akhir
    -0.07
    dialog
    -0.07
    orget
    -0.07
    POSITIVE LOGITS
    athan
    0.18
    nie
    0.12
    athon
    0.11
    atan
    0.10
    ston
    0.09
    ning
    0.08
    stone
    0.08
     Baptist
    0.08
    ni
    0.07
    annes
    0.07
    Activations Density 0.036%

    No Known Activations