© 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. 85290
    Prev
    Next
    INDEX
    Explanations

    individual and collective pronouns indicating involvement or actions taken by people

    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
     rest
    -0.07
    isÃŃ
    -0.07
     Gam
    -0.06
    ield
    -0.06
     dag
    -0.06
    å¯
    -0.06
    (cuda
    -0.06
    اعÙĬ
    -0.06
     soundtrack
    -0.06
    oho
    -0.06
    POSITIVE LOGITS
    abei
    0.07
    .twitter
    0.07
    okable
    0.07
    ekim
    0.07
    bservice
    0.06
    atham
    0.06
    ichel
    0.06
    ahr
    0.06
    .LENGTH
    0.06
    celed
    0.06
    Activations Density 0.018%

    No Known Activations