© 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. 22-LLAMASCOPE-RES-131K
    11. 4257
    Prev
    Next
    INDEX
    Explanations

    expressions of personal enjoyment and complex character interactions

    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
     -
    -0.07
     folks
    -0.07
    -0.06
     protections
    -0.06
     temper
    -0.06
     ðŁ
    -0.05
     W
    -0.05
    asure
    -0.05
     &
    -0.05
     support
    -0.05
    POSITIVE LOGITS
     اÙĦرÙħزÙĬØ©
    0.09
     freeze
    0.08
     Freeze
    0.08
    peÄį
    0.08
    ARGET
    0.07
    iqué
    0.07
    freeze
    0.07
    imson
    0.07
    .freeze
    0.07
    ÙĪÙĨØ©
    0.07
    Activations Density 0.002%

    No Known Activations