© 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. 74812
    Prev
    Next
    INDEX
    Explanations

    expressions of personal sentiment or emotional states

    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
    ½
    -0.07
     lately
    -0.07
    ongs
    -0.07
     Gerr
    -0.07
     ilk
    -0.07
     immediate
    -0.06
    å·²
    -0.06
    uddenly
    -0.06
    already
    -0.06
    веÑģÑĤи
    -0.06
    POSITIVE LOGITS
     ultimately
    0.17
     Ultimately
    0.14
    Ultimately
    0.14
    ult
    0.12
     ultimate
    0.12
     eventually
    0.11
     Eventually
    0.10
     eventual
    0.10
    Eventually
    0.10
     Ultimate
    0.09
    Activations Density 0.033%

    No Known Activations