© 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. 70964
    Prev
    Next
    INDEX
    Explanations

    references to specific ages or age groups and their context within narratives

    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
    enha
    -0.09
    âce
    -0.07
    ishlist
    -0.07
    altung
    -0.07
    insky
    -0.07
    erdem
    -0.07
    ivol
    -0.07
    æ°Ĺãģ«åħ¥
    -0.07
    onders
    -0.06
    gu
    -0.06
    POSITIVE LOGITS
    anner
    0.07
     hol
    0.06
    oda
    0.06
    ãĤĨ
    0.06
    ryan
    0.06
    .setAction
    0.06
    \Action
    0.06
     Takım
    0.05
    aille
    0.05
     GBP
    0.05
    Activations Density 0.015%

    No Known Activations