© 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. 31582
    Prev
    Next
    INDEX
    Explanations

    references to specific projects or initiatives

    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
     YaÅŁ
    -0.08
    isto
    -0.07
    REW
    -0.07
    ãĥ©ãĤ¤ãĥĪ
    -0.07
    sic
    -0.07
    ALER
    -0.07
    ãĤ¤ãĥ¤
    -0.06
     dispatched
    -0.06
    OMIC
    -0.06
    seau
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
    ĺìĿ´
    0.06
    aux
    0.06
    emd
    0.06
     yesterday
    0.06
    ála
    0.06
     mere
    0.06
    ely
    0.06
    tas
    0.06
     her
    0.05
    Activations Density 0.000%

    No Known Activations