© 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. 38450
    Prev
    Next
    INDEX
    Explanations

    information related to historical identities and significant events

    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
    emale
    -0.08
    иÑģлов
    -0.07
    ãĤ¢ãĥ¼
    -0.07
    ¶Į
    -0.07
    eyse
    -0.07
    eca
    -0.07
    @dynamic
    -0.06
     Madame
    -0.06
    eron
    -0.06
     MOCK
    -0.06
    POSITIVE LOGITS
    amt
    0.08
     Parish
    0.07
     records
    0.07
     parish
    0.07
    iges
    0.06
     given
    0.06
     barrel
    0.06
     Records
    0.06
    aker
    0.06
    entieth
    0.06
    Activations Density 0.003%

    No Known Activations