© 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. 1899
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic or administrative divisions, particularly parishes

    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
    ÑĢа
    -0.07
    SSID
    -0.06
     cellForRowAt
    -0.06
    outs
    -0.06
    egers
    -0.06
    erca
    -0.06
     outs
    -0.05
    ibold
    -0.05
    728
    -0.05
     Neb
    -0.05
    POSITIVE LOGITS
     елек
    0.08
    vor
    0.07
    Ø°
    0.07
    ãĥ¼ãĥĬ
    0.07
    (Arg
    0.07
    =row
    0.07
    orf
    0.07
    orph
    0.07
     PartialView
    0.06
     challenger
    0.06
    Activations Density 0.001%

    No Known Activations