© 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. 73890
    Prev
    Next
    INDEX
    Explanations

    reported speech or expressions of what people say

    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
    evin
    -0.07
    aÅŁ
    -0.07
    .mapbox
    -0.07
    ressing
    -0.07
    eon
    -0.07
    za
    -0.07
    sko
    -0.06
     ever
    -0.06
     Trot
    -0.06
    irt
    -0.06
    POSITIVE LOGITS
    odel
    0.07
    593
    0.06
     alike
    0.06
    (_,
    0.06
     cứ
    0.06
     بÙĪر
    0.06
    says
    0.06
    ableObject
    0.05
     Barbar
    0.05
     descent
    0.05
    Activations Density 0.026%

    No Known Activations