© 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. 38409
    Prev
    Next
    INDEX
    Explanations

    legal roles and relationships within a case context

    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
    asan
    -0.08
    _Tis
    -0.08
    theon
    -0.08
     mne
    -0.08
    eva
    -0.07
    .mit
    -0.07
    [".
    -0.07
    FRING
    -0.07
     ноÑĢмаÑĤив
    -0.07
    зÑı
    -0.07
    POSITIVE LOGITS
     estate
    0.07
    dba
    0.07
     vs
    0.06
     estates
    0.06
     blah
    0.06
     against
    0.06
     consolidated
    0.06
     av
    0.06
     affected
    0.06
     behalf
    0.06
    Activations Density 0.007%

    No Known Activations