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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 1323
    Prev
    Next
    INDEX
    Explanations

    quotes and attributed statements from 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
    ucene
    -0.08
    ancellable
    -0.08
    enko
    -0.08
    ibold
    -0.07
    /Dk
    -0.07
    tero
    -0.07
    atos
    -0.07
    akens
    -0.07
    alis
    -0.07
    istrovstvÃŃ
    -0.07
    POSITIVE LOGITS
     answer
    0.07
    ayan
    0.07
     interviewer
    0.07
    umd
    0.07
     denial
    0.06
    LEAR
    0.06
     bund
    0.06
    Asked
    0.06
     Bund
    0.06
    seg
    0.06
    Activations Density 0.023%

    No Known Activations