© 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. 116499
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups associated with certain actions or 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
    inecraft
    -0.07
    liqu
    -0.07
     Spirits
    -0.07
    RITE
    -0.07
    ukkit
    -0.06
    ordion
    -0.06
    sez
    -0.06
    129
    -0.06
    igin
    -0.06
    115
    -0.06
    POSITIVE LOGITS
    hammad
    0.08
    roe
    0.06
    nero
    0.06
    ammad
    0.06
    tual
    0.06
    vement
    0.06
    hb
    0.06
    oux
    0.06
    enthal
    0.06
     overall
    0.05
    Activations Density 0.025%

    No Known Activations