© 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. 86680
    Prev
    Next
    INDEX
    Explanations

    technical specifications and configurations in a programming or hardware context

    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
    AZY
    -0.08
    uong
    -0.07
    CHANT
    -0.07
    Fd
    -0.07
    ãĥĸãĥ«
    -0.07
    ibri
    -0.07
    812
    -0.07
     ê²ģ
    -0.07
    tha
    -0.07
    ItemAt
    -0.07
    POSITIVE LOGITS
     :
    0.06
     Nar
    0.06
     |
    0.06
     -
    0.06
     Gat
    0.06
     apro
    0.05
     (
    0.05
     ,
    0.05
    ,
    0.05
    ...
    0.05
    Activations Density 0.040%

    No Known Activations