© 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. 124365
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and words indicating inclusion or collective experience

    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
    .TEXTURE
    -0.07
    cke
    -0.07
    UFFIX
    -0.06
    cona
    -0.06
    ospace
    -0.06
     soon
    -0.06
     enim
    -0.06
     buá»Ļc
    -0.06
     oy
    -0.06
    inema
    -0.06
    POSITIVE LOGITS
    onto
    0.07
    velle
    0.06
    .DropDown
    0.06
    iese
    0.06
     Rol
    0.06
     Fair
    0.06
    rál
    0.06
     DISCLAIMER
    0.06
    yl
    0.06
     Skill
    0.06
    Activations Density 0.021%

    No Known Activations