© 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. 56463
    Prev
    Next
    INDEX
    Explanations

    instructions or guidelines related to product usage and preparation

    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
    /trunk
    -0.07
    274
    -0.06
    erap
    -0.06
    онов
    -0.06
     Held
    -0.06
    hawk
    -0.06
    emiz
    -0.06
    iker
    -0.06
    552
    -0.06
    ever
    -0.06
    POSITIVE LOGITS
     instructions
    0.12
    instructions
    0.10
     Instructions
    0.09
     directions
    0.09
     инÑģÑĤÑĢÑĥк
    0.09
     instruction
    0.09
    Instructions
    0.08
     instr
    0.08
     manufacturer
    0.08
    .radians
    0.08
    Activations Density 0.012%

    No Known Activations