© 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. 90103
    Prev
    Next
    INDEX
    Explanations

    terms related to gas and electric appliances

    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
    adolu
    -0.07
    /loose
    -0.07
    çĶ
    -0.07
    Ñģли
    -0.06
     oversight
    -0.06
    AGO
    -0.06
    specifier
    -0.06
     aile
    -0.06
    resse
    -0.06
    "user
    -0.06
    POSITIVE LOGITS
    tember
    0.07
    ichen
    0.07
    cca
    0.06
    olen
    0.06
    iani
    0.06
    ereg
    0.06
    -fed
    0.06
    751
    0.06
    isé
    0.06
    uma
    0.06
    Activations Density 0.001%

    No Known Activations