© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57929
    Prev
    Next
    INDEX
    Explanations

    formal reporting structure and citation of sources

    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
    ble
    -0.07
    atori
    -0.07
     Granite
    -0.06
    astr
    -0.06
    RF
    -0.06
    ейн
    -0.06
    elan
    -0.06
    612
    -0.05
     decorated
    -0.05
    bast
    -0.05
    POSITIVE LOGITS
     Pager
    0.07
    ourke
    0.07
    addir
    0.07
    zek
    0.07
    )NULL
    0.06
     Roe
    0.06
    šel
    0.06
    nings
    0.06
    isons
    0.06
    OMBRE
    0.06
    Activations Density 0.013%

    No Known Activations