© 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. 54307
    Prev
    Next
    INDEX
    Explanations

    references to locations and accommodations

    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
    975
    -0.07
    972
    -0.06
     Tide
    -0.06
     Isles
    -0.06
    homme
    -0.06
    990
    -0.06
    670
    -0.06
    ivan
    -0.06
    heimer
    -0.05
    ariat
    -0.05
    POSITIVE LOGITS
     å¾ĴæŃ©
    0.08
    LAY
    0.08
    .::
    0.08
    æŃ´
    0.08
     [~,
    0.07
    ãĥ¼ãĥĦ
    0.07
    @js
    0.07
     ----------------------------------------------------------------------------↵
    0.07
    oland
    0.07
    abwe
    0.07
    Activations Density 0.025%

    No Known Activations