© 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. 108144
    Prev
    Next
    INDEX
    Explanations

    conditional statements and scenarios involving choices or contingencies

    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
    лоÑĢ
    -0.07
    éc
    -0.07
    .tc
    -0.07
    ibili
    -0.07
    é¦Ļ
    -0.07
    ekler
    -0.07
    ingleton
    -0.06
     Sands
    -0.06
    ibile
    -0.06
    bia
    -0.06
    POSITIVE LOGITS
     needs
    0.13
     needed
    0.13
     Needed
    0.11
    éľĢè¦ģ
    0.11
     need
    0.11
    needed
    0.11
     Needs
    0.10
    needs
    0.10
     needing
    0.10
     Need
    0.10
    Activations Density 0.077%

    No Known Activations