© 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. 17788
    Prev
    Next
    INDEX
    Explanations

    phrases related to charitable activities and community support

    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
    Wed
    -0.07
    ORITY
    -0.06
    azio
    -0.06
    ÅĻez
    -0.06
    wed
    -0.06
    iever
    -0.06
    ANGLES
    -0.06
    achten
    -0.06
    Ïģί
    -0.06
     اÙĦÙħÙģ
    -0.06
    POSITIVE LOGITS
     cancer
    0.09
     Cancer
    0.09
     Relay
    0.08
     Participant
    0.07
    lea
    0.07
     participant
    0.07
     pits
    0.07
     cancers
    0.06
    Registration
    0.06
     Walk
    0.06
    Activations Density 0.004%

    No Known Activations