© 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. 124262
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to personal relationships and connections

    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
     Gilbert
    -0.08
    лиÑĪ
    -0.07
    ếp
    -0.07
    воÑİ
    -0.07
    úb
    -0.07
    okino
    -0.07
    ighton
    -0.07
    ï¼Ĵï¼IJ
    -0.07
    ahu
    -0.07
    ltk
    -0.07
    POSITIVE LOGITS
    /us
    0.07
    87
    0.06
     imm
    0.06
     ap
    0.06
    umm
    0.05
    alt
    0.05
    omen
    0.05
     pits
    0.05
     diving
    0.05
    urs
    0.05
    Activations Density 0.038%

    No Known Activations