© 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. 118925
    Prev
    Next
    INDEX
    Explanations

    structured data or formatting elements within a document

    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
     set
    -0.06
    mini
    -0.05
    int
    -0.05
    aine
    -0.05
    ani
    -0.05
    ubat
    -0.05
    agan
    -0.05
    ulp
    -0.05
    275
    -0.05
    intern
    -0.05
    POSITIVE LOGITS
     éĸ
    0.08
    okino
    0.07
    غÙĨ
    0.07
    eum
    0.07
    ÑĶм
    0.07
    Ïģκε
    0.07
    feld
    0.07
    eor
    0.07
    á»ı
    0.07
    !!!!↵↵
    0.07
    Activations Density 0.000%

    No Known Activations