© 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. 17-LLAMASCOPE-RES-131K
    11. 56763
    Prev
    Next
    INDEX
    Explanations

    instances of individual names and their associated actions or context

    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
    igua
    -0.07
    its
    -0.07
    uesta
    -0.06
    Edit
    -0.06
    asper
    -0.06
    ellig
    -0.06
    awns
    -0.06
    iene
    -0.06
    oppel
    -0.06
     Neptune
    -0.06
    POSITIVE LOGITS
     whose
    0.10
     who
    0.10
    whose
    0.08
     which
    0.08
     który
    0.08
     himself
    0.07
     winner
    0.07
    who
    0.07
     cui
    0.07
     koji
    0.07
    Activations Density 0.016%

    No Known Activations