© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60643
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-identity and understanding personal experiences

    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
    енка
    -0.08
    ifest
    -0.07
    ervers
    -0.07
    .footer
    -0.07
    (æľ¨
    -0.06
    们
    -0.06
     lith
    -0.06
     stray
    -0.06
    ucci
    -0.06
    eyse
    -0.06
    POSITIVE LOGITS
    -controls
    0.06
    leDb
    0.06
    iect
    0.06
     Counties
    0.06
    andas
    0.06
    oca
    0.06
    gent
    0.06
     never
    0.06
    hc
    0.06
    Łèĥ½
    0.06
    Activations Density 0.047%

    No Known Activations