© 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. 103958
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of need or necessity

    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
     Trab
    -0.08
    ivi
    -0.07
    udad
    -0.07
    ÑĥÑĤÑĮ
    -0.07
    isson
    -0.07
    ÃŃstica
    -0.07
    ysters
    -0.06
     Fog
    -0.06
     tavs
    -0.06
    kit
    -0.06
    POSITIVE LOGITS
    lessly
    0.10
    iness
    0.08
    ful
    0.08
    ìĤ¬íķŃ
    0.07
    iest
    0.07
    lingen
    0.07
    erm
    0.07
    ier
    0.07
    fulness
    0.07
    spot
    0.06
    Activations Density 0.008%

    No Known Activations