© 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. 17-LLAMASCOPE-RES-131K
    11. 55961
    Prev
    Next
    INDEX
    Explanations

    phrases related to selecting or making choices

    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
     purpose
    -0.08
    cott
    -0.08
     Purpose
    -0.07
    Purpose
    -0.07
     purposes
    -0.07
     defeat
    -0.07
    purpose
    -0.07
    té
    -0.07
     point
    -0.07
     PURPOSE
    -0.06
    POSITIVE LOGITS
     suits
    0.12
     suited
    0.09
     best
    0.09
     suit
    0.09
     Suit
    0.08
    suit
    0.08
    best
    0.07
     phù
    0.07
    aniel
    0.07
    Interop
    0.07
    Activations Density 0.067%

    No Known Activations