© 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. 81476
    Prev
    Next
    INDEX
    Explanations

    positive experiences related to gardening, community, and personal contributions

    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
    èķ
    -0.07
    £
    -0.06
    akk
    -0.06
    sil
    -0.06
     Panama
    -0.06
     ست
    -0.06
     Reform
    -0.05
     eth
    -0.05
     pleasing
    -0.05
    iro
    -0.05
    POSITIVE LOGITS
    åıĤåĬł
    0.09
     participants
    0.09
     Participant
    0.08
     Participants
    0.08
     participant
    0.08
     participation
    0.08
    Participants
    0.08
     ì°¸ìŬ
    0.08
    Participant
    0.08
     participates
    0.07
    Activations Density 0.003%

    No Known Activations