© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26500
    Prev
    Next
    INDEX
    Explanations

    instances of guidance or advice related to problem-solving and providing solutions

    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
     STRICT
    -0.06
    наÑĢÑĥж
    -0.06
    arton
    -0.06
    >[]
    -0.06
    ccak
    -0.06
    ackers
    -0.06
    ÃľM
    -0.06
    odox
    -0.06
    kee
    -0.06
    ige
    -0.06
    POSITIVE LOGITS
    æıIJä¾Ľ
    0.07
    Concrete
    0.07
    åħ·ä½ĵ
    0.07
     concrete
    0.07
     accompanied
    0.07
     provide
    0.07
     provides
    0.07
     Concrete
    0.07
     providing
    0.06
    ands
    0.06
    Activations Density 0.074%

    No Known Activations