© 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. 15065
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and their usage in context

    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
     himself
    -0.09
     itself
    -0.09
     herself
    -0.08
    ÑĢог
    -0.07
     siÄĻ
    -0.07
     zich
    -0.07
     themselves
    -0.07
    tight
    -0.07
     myself
    -0.07
    immel
    -0.06
    POSITIVE LOGITS
    zelf
    0.10
    /us
    0.07
    еление
    0.07
    NSError
    0.06
    unes
    0.06
     Cove
    0.06
    eno
    0.06
     Vul
    0.06
    chant
    0.06
    'icon
    0.06
    Activations Density 0.018%

    No Known Activations