© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 127454
    Prev
    Next
    INDEX
    Explanations

    expressions of relief or contentment

    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
    ieber
    -0.06
    رÙĪت
    -0.06
    ahr
    -0.06
     liá»ĩu
    -0.06
     Jo
    -0.06
    aida
    -0.06
    LK
    -0.06
    ROP
    -0.06
     merit
    -0.06
    gba
    -0.06
    POSITIVE LOGITS
     finally
    0.08
     didn
    0.08
    idak
    0.07
    didn
    0.07
    pell
    0.07
    finally
    0.07
    osen
    0.07
    andin
    0.07
    822
    0.06
    uess
    0.06
    Activations Density 0.023%

    No Known Activations