© 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. 80771
    Prev
    Next
    INDEX
    Explanations

    references to actions or events related to functionality in a development or programming context

    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
    ear
    -0.06
    oter
    -0.06
    477
    -0.06
    omens
    -0.06
     Uhr
    -0.06
    485
    -0.05
    791
    -0.05
    362
    -0.05
    365
    -0.05
    igy
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.11
     pathMatch
    0.09
     arası
    0.08
    KeyId
    0.07
    sdale
    0.07
    oria
    0.07
    avier
    0.07
    eyin
    0.07
    åľŃ
    0.07
    ocker
    0.07
    Activations Density 0.000%

    No Known Activations