© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26989
    Prev
    Next
    INDEX
    Explanations

    occurrences of method calls related to getting and setting values within a programming 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
    theless
    -0.08
    Type
    -0.08
    ity
    -0.08
    ushima
    -0.07
    KeyType
    -0.07
    Ø©
    -0.07
    yc
    -0.07
    ly
    -0.07
    atic
    -0.07
    Name
    -0.07
    POSITIVE LOGITS
    ters
    0.12
    tings
    0.10
    TERS
    0.09
    tin
    0.08
    OrDefault
    0.08
    TING
    0.08
    681
    0.08
    ernote
    0.07
    /set
    0.07
    zl
    0.07
    Activations Density 0.031%

    No Known Activations