© 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. 59292
    Prev
    Next
    INDEX
    Explanations

    references to upcoming releases and durations related to media content

    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
     ("
    -0.06
    [at
    -0.06
     («
    -0.06
    wers
    -0.06
     /
    -0.06
     tslib
    -0.06
     ev
    -0.06
    ÑĢÑĸд
    -0.06
    .router
    -0.05
    .heroku
    -0.05
    POSITIVE LOGITS
    inish
    0.08
    echa
    0.07
    alist
    0.07
    kk
    0.07
    ymi
    0.07
    ãĥ¼ãĥĨ
    0.07
    .scalablytyped
    0.07
    idal
    0.07
     =============================================================================↵
    0.06
    bow
    0.06
    Activations Density 0.000%

    No Known Activations