© 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. 126917
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-awareness and personal growth

    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
    rip
    -0.07
    ayd
    -0.07
    aleb
    -0.07
    itia
    -0.06
     ника
    -0.06
    roken
    -0.06
     Johns
    -0.06
    aho
    -0.06
     footer
    -0.06
     nicknamed
    -0.06
    POSITIVE LOGITS
     ourselves
    0.14
     abych
    0.08
     often
    0.07
    æĪijåĢij
    0.07
    chg
    0.07
    Ñħодим
    0.07
    بط
    0.07
    often
    0.07
    ervlet
    0.07
    LTE
    0.07
    Activations Density 0.110%

    No Known Activations