© 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. 106041
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal reflections or expressions of feelings

    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
     too
    -0.16
     TOO
    -0.15
     Too
    -0.15
    Too
    -0.14
    too
    -0.14
    太
    -0.14
     demasi
    -0.12
    -too
    -0.11
    _TOO
    -0.11
     ÑģлиÑĪком
    -0.11
    POSITIVE LOGITS
    æ¸Ī
    0.06
    icator
    0.06
    ire
    0.06
     Conflict
    0.06
    anter
    0.06
    ivic
    0.06
    ullen
    0.06
    ira
    0.05
     Sew
    0.05
    éļł
    0.05
    Activations Density 0.012%

    No Known Activations