© 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. 94865
    Prev
    Next
    INDEX
    Explanations

    cooking techniques and types of prepared foods

    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
    ople
    -0.07
    igator
    -0.07
    quier
    -0.06
    ense
    -0.06
    uild
    -0.06
    }elseif
    -0.06
    hee
    -0.06
    ksam
    -0.06
    quia
    -0.06
    inki
    -0.06
    POSITIVE LOGITS
    "data
    0.06
     "','
    0.06
    ernes
    0.06
    iegel
    0.06
    оÑĤв
    0.06
     Hayward
    0.06
    edl
    0.06
    iggs
    0.06
    ụ
    0.06
     Berk
    0.06
    Activations Density 0.014%

    No Known Activations