© 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. 118569
    Prev
    Next
    INDEX
    Explanations

    key components and features related to artistic practices or cultural elements

    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
    arih
    -0.06
     EXCEPTION
    -0.06
    ToLocal
    -0.06
    deo
    -0.06
    acea
    -0.06
    emer
    -0.06
    olest
    -0.06
    ron
    -0.06
    å®ħ
    -0.06
    enstein
    -0.05
    POSITIVE LOGITS
     feature
    0.14
    feature
    0.13
     Feature
    0.11
     characteristic
    0.11
    Feature
    0.11
     element
    0.11
    _feature
    0.10
     features
    0.10
    features
    0.10
     FEATURE
    0.10
    Activations Density 0.089%

    No Known Activations