© 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. 92920
    Prev
    Next
    INDEX
    Explanations

    numerical information related to employee counts and organizational size

    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
    anders
    -0.08
     addCriterion
    -0.07
    ander
    -0.07
    ÑĢÑĥÑģ
    -0.07
    ört
    -0.07
    еÑĢÑĤи
    -0.07
    ispens
    -0.07
    borough
    -0.07
    arme
    -0.07
    asso
    -0.07
    POSITIVE LOGITS
     employees
    0.13
     employee
    0.10
     Employees
    0.10
    employees
    0.10
     staff
    0.09
    Employees
    0.09
    employee
    0.08
     workers
    0.08
    åĵ¡
    0.07
    åijĺ
    0.07
    Activations Density 0.007%

    No Known Activations