Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96002
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to jurisdiction and case status

    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
    opensource
    -0.07
    isplay
    -0.07
    arend
    -0.06
    pared
    -0.06
    abox
    -0.06
     Invalidate
    -0.06
    oking
    -0.06
    esty
    -0.06
     wards
    -0.06
    ány
    -0.06
    POSITIVE LOGITS
    ampa
    0.07
     Zig
    0.06
     Lennon
    0.06
    786
    0.06
     Bast
    0.06
    ÙĤÙĪÙĦ
    0.06
    Abr
    0.06
    OSH
    0.06
    ·
    0.06
    .Dictionary
    0.06
    Activations Density 0.027%

    No Known Activations