© 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. 9-LLAMASCOPE-RES-131K
    11. 98030
    Prev
    Next
    INDEX
    Explanations

    conversational language that indicates discussing one's thoughts or opinions

    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
    帽
    -0.06
     MagicMock
    -0.06
    енÑĮÑİ
    -0.06
    wich
    -0.06
     vac
    -0.06
    Ä©nh
    -0.06
    RICT
    -0.06
     McKin
    -0.06
    ocs
    -0.06
    æ
    -0.06
    POSITIVE LOGITS
     kontakte
    0.07
    inson
    0.07
    ayet
    0.06
    หาร
    0.06
    ute
    0.06
    ãĥ¼ãĥķ
    0.06
    μÎŃ
    0.06
    .mixin
    0.06
    åīµ
    0.06
    eer
    0.06
    Activations Density 0.011%

    No Known Activations