© 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. 91755
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect assessment or evaluation of situations

    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
    اذا
    -0.07
    ť
    -0.07
    ominator
    -0.07
    _LP
    -0.07
    ermalink
    -0.07
    okit
    -0.07
    OGRAPH
    -0.07
    AFX
    -0.07
    CEED
    -0.07
    Äįka
    -0.07
    POSITIVE LOGITS
     how
    0.10
     that
    0.09
     what
    0.08
     its
    0.07
     the
    0.07
     it
    0.07
    á
    0.07
     there
    0.07
     fact
    0.07
     they
    0.07
    Activations Density 0.007%

    No Known Activations