© 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 EvalsExportsAPI 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. 61030
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes or steps in a task

    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
    oi
    -0.06
    į
    -0.06
    ropri
    -0.06
    ź
    -0.06
    abel
    -0.06
     Äijoán
    -0.06
    ights
    -0.05
     quen
    -0.05
     Haut
    -0.05
    ape
    -0.05
    POSITIVE LOGITS
    mpp
    0.07
    OUCH
    0.07
    URAL
    0.07
    ãĥ¼ãĤ¿ãĥ¼
    0.07
    loh
    0.07
    riad
    0.07
    IOUS
    0.06
    angl
    0.06
    ified
    0.06
    Bron
    0.06
    Activations Density 0.005%

    No Known Activations