© 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. 16654
    Prev
    Next
    INDEX
    Explanations

    adjectives describing complex or challenging situations

    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
    jd
    -0.06
     mimo
    -0.05
    azu
    -0.05
     Gain
    -0.05
    rix
    -0.05
    ystems
    -0.05
    idth
    -0.05
    кÑģ
    -0.05
    /Area
    -0.05
     Useful
    -0.05
    POSITIVE LOGITS
     nature
    0.18
    nature
    0.15
     Nature
    0.11
     manner
    0.10
    Nature
    0.10
    ness
    0.10
    æĢ§
    0.10
     role
    0.09
     way
    0.09
     بÙĪدÙĨ
    0.08
    Activations Density 0.088%

    No Known Activations