© 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. 80631
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for," indicating a focus on purpose or rationale

    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
    ola
    -0.07
    idis
    -0.07
    isay
    -0.06
    aki
    -0.06
    acz
    -0.06
     ÑĥÑĩиÑĤ
    -0.06
    hof
    -0.06
    ter
    -0.06
    ylon
    -0.06
    esp
    -0.06
    POSITIVE LOGITS
     example
    0.15
     instance
    0.13
     exemplo
    0.10
     ejemplo
    0.10
    instance
    0.10
    example
    0.10
     Example
    0.10
    _example
    0.09
     exemple
    0.09
    ä¾ĭ
    0.09
    Activations Density 0.009%

    No Known Activations