© 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. 81896
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial and agricultural applications of materials

    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
    .getSelectionModel
    -0.07
    ï¼Īç¬ij
    -0.07
    itone
    -0.07
    æı®
    -0.06
    Æ°á»Łng
    -0.06
    å¹¹
    -0.06
    amped
    -0.06
    aser
    -0.06
    imes
    -0.06
     agg
    -0.06
    POSITIVE LOGITS
     purposes
    0.11
    apia
    0.07
     applications
    0.07
     каÑĩеÑģÑĤве
    0.06
    -grade
    0.06
    -Compatible
    0.06
    Uses
    0.06
     uses
    0.06
    alette
    0.06
    fst
    0.06
    Activations Density 0.053%

    No Known Activations