© 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. 94158
    Prev
    Next
    INDEX
    Explanations

    expressions of good wishes and positive sentiments towards others

    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
    eyin
    -0.09
    ίκ
    -0.09
    _bases
    -0.08
    IFEST
    -0.07
    eam
    -0.07
    optera
    -0.07
    matter
    -0.07
    reative
    -0.07
    áºŃt
    -0.07
     Äįin
    -0.07
    POSITIVE LOGITS
     success
    0.09
    success
    0.07
     luck
    0.07
    enda
    0.07
     Success
    0.06
    Success
    0.06
     happy
    0.06
     fortunes
    0.06
     succes
    0.06
     ØŃاÙĦÛĮ
    0.06
    Activations Density 0.005%

    No Known Activations