© 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. 94483
    Prev
    Next
    INDEX
    Explanations

    instances of verbs and their forms

    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
    iswa
    -0.07
    anki
    -0.07
    imens
    -0.07
    cco
    -0.07
    apur
    -0.07
    ittest
    -0.06
    stroy
    -0.06
    ifu
    -0.06
    summ
    -0.06
    wend
    -0.06
    POSITIVE LOGITS
     Tu
    0.07
    CLUDING
    0.07
    alach
    0.06
    AINED
    0.06
     Vet
    0.06
    iž
    0.06
    oret
    0.06
     Walt
    0.06
     including
    0.05
    atal
    0.05
    Activations Density 0.042%

    No Known Activations