© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106087
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and phrases indicating invitations or requests

    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
    ãĤ¥
    -0.07
    quires
    -0.06
    393
    -0.06
    yr
    -0.06
    iegel
    -0.06
    æĿ
    -0.06
    ÑĥÑĢе
    -0.06
    ún
    -0.06
    asper
    -0.06
    kara
    -0.06
    POSITIVE LOGITS
     participate
    0.08
     join
    0.08
     Particip
    0.07
    åĬłåħ¥
    0.07
     prest
    0.07
    isher
    0.07
    åıĤåĬł
    0.07
    join
    0.07
     particip
    0.07
    meet
    0.06
    Activations Density 0.010%

    No Known Activations