© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31289
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    opia
    -0.06
    hydr
    -0.06
    io
    -0.06
     Rim
    -0.06
    og
    -0.06
    ence
    -0.06
    adol
    -0.06
     Cone
    -0.06
    çon
    -0.06
     within
    -0.06
    POSITIVE LOGITS
    JOB
    0.08
     bosses
    0.07
    amba
    0.07
     boss
    0.07
    obus
    0.07
    lesia
    0.07
    Crime
    0.07
    eken
    0.07
    .family
    0.07
    GUID
    0.06
    Activations Density 0.037%

    No Known Activations