© 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. 70943
    Prev
    Next
    INDEX
    Explanations

    family names and relationships

    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
    ви
    -0.07
    оком
    -0.06
    apr
    -0.06
     <<-
    -0.06
    eyJ
    -0.06
     stru
    -0.06
    ansi
    -0.06
    asz
    -0.06
    reib
    -0.06
    elerik
    -0.06
    POSITIVE LOGITS
    ová
    0.07
    ipple
    0.06
     spouse
    0.06
    stakes
    0.06
     spouses
    0.06
    gard
    0.06
    iller
    0.06
    OLUTE
    0.06
    ignKey
    0.06
    UILayout
    0.06
    Activations Density 0.011%

    No Known Activations