© 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. 79465
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and conditional logic structures

    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
    ahoo
    -0.07
    TeV
    -0.07
    اخ
    -0.07
    izo
    -0.06
    ãĥ³ãĥĦ
    -0.06
    rung
    -0.06
    lz
    -0.06
     {?>↵
    -0.06
    ose
    -0.06
    ê·¹
    -0.06
    POSITIVE LOGITS
    .stopPropagation
    0.09
    .Handled
    0.09
     prevent
    0.09
     return
    0.08
     prevention
    0.08
    prevent
    0.08
    return
    0.07
     prevents
    0.07
    .preventDefault
    0.07
     preventing
    0.07
    Activations Density 0.033%

    No Known Activations