© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62008
    Prev
    Next
    INDEX
    Explanations

    specific locations and their associated amenities or features

    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
    asl
    -0.07
    .hu
    -0.06
    :black
    -0.06
    avl
    -0.06
     Gap
    -0.06
    GAN
    -0.06
    istry
    -0.06
    ocket
    -0.06
    anmar
    -0.06
    cq
    -0.06
    POSITIVE LOGITS
    meli
    0.08
    chemas
    0.07
    addir
    0.07
    ersiz
    0.07
     Marshal
    0.06
     IonicModule
    0.06
     Shadows
    0.06
    ocha
    0.06
    mÃŃ
    0.06
    -transitional
    0.06
    Activations Density 0.108%

    No Known Activations