© 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. 118968
    Prev
    Next
    INDEX
    Explanations

    phrases that denote quantities or lists of items

    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
    amen
    -0.06
    ẫn
    -0.06
    stood
    -0.06
    à¥įतम
    -0.06
    WithValue
    -0.06
     lẫn
    -0.06
    OTE
    -0.06
    .dtd
    -0.06
    -Cs
    -0.06
     tens
    -0.06
    POSITIVE LOGITS
     ways
    0.10
    fold
    0.08
     reasons
    0.08
    anje
    0.08
     Ways
    0.07
    -fold
    0.07
    ï¸ı
    0.07
     things
    0.06
    anki
    0.06
    thers
    0.06
    Activations Density 0.006%

    No Known Activations