© 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. 28240
    Prev
    Next
    INDEX
    Explanations

    phrases related to the functionality of electronic devices

    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
    ongan
    -0.08
    asso
    -0.07
    ertino
    -0.07
    ymph
    -0.07
    awn
    -0.07
     CrossAxisAlignment
    -0.07
    ubre
    -0.07
    apot
    -0.07
    atown
    -0.06
     é¹
    -0.06
    POSITIVE LOGITS
    ãĥīãĥ«
    0.06
    pu
    0.06
    ory
    0.06
    adow
    0.06
     background
    0.06
     inher
    0.06
     weighing
    0.06
     SRC
    0.06
     sentence
    0.05
    beh
    0.05
    Activations Density 0.000%

    No Known Activations