© 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. 76218
    Prev
    Next
    INDEX
    Explanations

    definitions and details related to loan programs and financial assistance

    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
    .scalablytyped
    -0.08
     neon
    -0.06
     Innoc
    -0.06
    931
    -0.06
     dr
    -0.06
    åĿĽ
    -0.06
    LANGUAGE
    -0.06
    æı®
    -0.06
     drill
    -0.06
    filer
    -0.06
    POSITIVE LOGITS
     Kauf
    0.07
    ailable
    0.07
    -overlay
    0.06
    idlo
    0.06
    ordes
    0.06
    abay
    0.06
     Program
    0.06
     Mills
    0.06
     FHA
    0.06
    ela
    0.06
    Activations Density 0.002%

    No Known Activations