© 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. 108932
    Prev
    Next
    INDEX
    Explanations

    numerical references or values related to decision-making contexts

    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
    iesz
    -0.06
     Bust
    -0.06
    lett
    -0.06
     Ipsum
    -0.06
    serter
    -0.06
     ÙĨاØŃ
    -0.06
    adius
    -0.06
     improv
    -0.06
    ismu
    -0.06
    odo
    -0.06
    POSITIVE LOGITS
     @
    0.09
    @g
    0.08
    @
    0.07
    @c
    0.07
    Offsets
    0.07
    .@
    0.07
     tong
    0.06
    ãģ¾ãģŁ
    0.06
     hi
    0.06
     amen
    0.06
    Activations Density 0.000%

    No Known Activations