© 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. 106399
    Prev
    Next
    INDEX
    Explanations

    references to Ayn Rand and her philosophical ideas

    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
    adal
    -0.07
    uzey
    -0.07
     Alphabet
    -0.06
     вин
    -0.06
    moth
    -0.06
     democrat
    -0.06
    ocha
    -0.06
    iona
    -0.06
    DeltaTime
    -0.06
     hil
    -0.06
    POSITIVE LOGITS
     Libertarian
    0.13
     libertarian
    0.12
     Freedom
    0.10
     liberty
    0.10
     libert
    0.10
     free
    0.09
     Libert
    0.09
     freedom
    0.09
     laisse
    0.09
     Liberty
    0.09
    Activations Density 0.179%

    No Known Activations