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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44063
    Prev
    Next
    INDEX
    Explanations

    indicators of problems or warning signs in various contexts

    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
    .sponge
    -0.07
    .scalablytyped
    -0.06
    lashes
    -0.06
    venge
    -0.06
    angan
    -0.06
    اÙĪÛĮ
    -0.05
     ÑģпÑĢав
    -0.05
    ffffffff
    -0.05
     geil
    -0.05
    argar
    -0.05
    POSITIVE LOGITS
     signs
    0.21
     warning
    0.20
     indicators
    0.20
     signals
    0.20
     clues
    0.19
     indications
    0.18
     tell
    0.18
     indicator
    0.18
     red
    0.17
     Signs
    0.17
    Activations Density 0.054%

    No Known Activations