© 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. 15231
    Prev
    Next
    INDEX
    Explanations

    components or specifications related to software or systems in lists or instructions

    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
    onden
    -0.07
    unden
    -0.07
    fait
    -0.06
    @student
    -0.06
    fbe
    -0.06
    Assignable
    -0.06
     =&
    -0.06
     &$
    -0.06
    elib
    -0.06
    plib
    -0.06
    POSITIVE LOGITS
     Holt
    0.07
    .gameserver
    0.07
    ±Ð¾ÑĤ
    0.06
    ocker
    0.06
    SupportActionBar
    0.06
    .volley
    0.06
    islav
    0.06
    .LayoutStyle
    0.06
     ?,
    0.06
     aka
    0.06
    Activations Density 0.020%

    No Known Activations