© 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. 5-LLAMASCOPE-RES-131K
    11. 126040
    Prev
    Next
    INDEX
    Explanations

    commands related to configuring and controlling hardware pins in code

    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
    erb
    -0.07
    meer
    -0.06
    ÙĦب
    -0.06
    bak
    -0.06
    ool
    -0.06
    lings
    -0.06
    otti
    -0.06
    ri
    -0.06
    lify
    -0.06
    nt
    -0.06
    POSITIVE LOGITS
    udad
    0.07
    stell
    0.07
    nice
    0.07
    ponent
    0.07
    -driven
    0.06
    urge
    0.06
    entlich
    0.06
    preh
    0.06
    regn
    0.06
    REFERRED
    0.06
    Activations Density 0.002%

    No Known Activations