© 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. 87574
    Prev
    Next
    INDEX
    Explanations

    references to various human needs and rights

    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
    AZE
    -0.07
    oven
    -0.07
    lor
    -0.07
    anner
    -0.07
    assin
    -0.07
    ãĥ©ãĥĥãĤ¯
    -0.07
    aku
    -0.07
    eland
    -0.06
    ัà¸ķ
    -0.06
    mojom
    -0.06
    POSITIVE LOGITS
     needs
    0.18
     Needs
    0.15
    needs
    0.14
    Needs
    0.12
     demands
    0.12
     requirements
    0.10
    éľĢæ±Ĥ
    0.10
     wants
    0.10
     demand
    0.09
     Requirements
    0.09
    Activations Density 0.078%

    No Known Activations