© 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. 17-LLAMASCOPE-RES-131K
    6. 126988
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to court opinions and rulings

    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
    //{{
    -0.06
    anut
    -0.06
    kelig
    -0.06
     Moreno
    -0.06
    меÑĩ
    -0.06
     veter
    -0.06
     Horizon
    -0.06
    ppo
    -0.06
    olini
    -0.06
    atre
    -0.06
    POSITIVE LOGITS
     bush
    0.07
    addtogroup
    0.07
    EMY
    0.06
    TOTYPE
    0.06
    !=(
    0.06
    ê´
    0.06
    endi
    0.06
    elman
    0.06
     lam
    0.06
    åĶĩ
    0.06
    Activations Density 0.017%

    No Known Activations