© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31391
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and actions related to individual or collective experiences

    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
    enga
    -0.07
    ersiz
    -0.07
     бÑĥ
    -0.07
    ëıĦìĿĺ
    -0.07
    keiten
    -0.07
    elow
    -0.07
    iants
    -0.07
    AGMA
    -0.07
    CALL
    -0.07
    èĢĮ
    -0.07
    POSITIVE LOGITS
    deaux
    0.06
     Byrne
    0.06
    ocre
    0.06
    ever
    0.06
     próp
    0.06
    769
    0.06
    VEC
    0.06
    BY
    0.06
     can
    0.06
     net
    0.06
    Activations Density 0.039%

    No Known Activations