© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31571
    Prev
    Next
    INDEX
    Explanations

    phrases related to future actions or commitments

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    alue
    -0.07
    UIL
    -0.06
    á»±a
    -0.06
    ÑĢади
    -0.06
    ìĦŃ
    -0.06
    (CG
    -0.06
    -widgets
    -0.06
     سÙĦاÙħ
    -0.06
    _Release
    -0.06
    ille
    -0.06
    POSITIVE LOGITS
    iao
    0.06
    optim
    0.06
    ÙIJر
    0.06
    imm
    0.06
    ģı
    0.06
    ords
    0.06
    ä¹ħ
    0.06
    tail
    0.06
    ICA
    0.06
    èĪ
    0.06
    Activations Density 0.009%

    No Known Activations