© 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. 69224
    Prev
    Next
    INDEX
    Explanations

    discussions about responses to significant events or issues

    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
    .typ
    -0.07
    etro
    -0.07
    eko
    -0.07
    alternative
    -0.07
    代
    -0.07
    onto
    -0.07
     alternative
    -0.07
    ãĥĪãĥ«
    -0.07
    isman
    -0.06
    æĽ¿
    -0.06
    POSITIVE LOGITS
     stimuli
    0.10
     request
    0.10
     requests
    0.10
     demands
    0.10
     needs
    0.09
    request
    0.08
     stimulus
    0.08
    请æ±Ĥ
    0.08
     demand
    0.08
     Needs
    0.08
    Activations Density 0.040%

    No Known Activations