© 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. 54882
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to leadership and management positions

    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
    Trivia
    -0.08
    ocoa
    -0.07
    alars
    -0.07
    likes
    -0.07
    ascript
    -0.07
    otron
    -0.06
     ciz
    -0.06
    sci
    -0.06
     odv
    -0.06
    asia
    -0.06
    POSITIVE LOGITS
     Holmes
    0.06
     said
    0.06
     ‘
    0.06
    åĪ¶
    0.06
     mana
    0.06
    (strtolower
    0.06
    人ãģ¯
    0.05
    plings
    0.05
     spokesperson
    0.05
    ERING
    0.05
    Activations Density 0.022%

    No Known Activations