© 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 EvalsExportsAPI 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. 82996
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and their biographical details

    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
     Folding
    -0.07
    ocket
    -0.06
     Fold
    -0.06
     fold
    -0.06
    abbr
    -0.06
    .enterprise
    -0.06
    hazi
    -0.06
     inter
    -0.06
    cente
    -0.06
    ustin
    -0.06
    POSITIVE LOGITS
     born
    0.20
     Born
    0.17
    Born
    0.16
    born
    0.15
    -born
    0.14
    çĶŁ
    0.13
     birth
    0.12
    çĶŁçļĦ
    0.11
     native
    0.10
     çĶŁ
    0.10
    Activations Density 0.046%

    No Known Activations