© 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. 105663
    Prev
    Next
    INDEX
    Explanations

    references to the name "Sah" and its variations, indicating a focus on individuals or concepts associated with that name

    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
    lys
    -0.07
    翼
    -0.07
    pcodes
    -0.07
    ymoon
    -0.07
    ongs
    -0.07
    burgh
    -0.07
    isos
    -0.07
    chaft
    -0.06
    rava
    -0.06
    rung
    -0.06
    POSITIVE LOGITS
    ̣
    0.09
    rschein
    0.07
    olics
    0.07
    Ñģклад
    0.07
    ovic
    0.07
    stile
    0.07
    s
    0.06
    cene
    0.06
    ĥn
    0.06
    gers
    0.06
    Activations Density 0.071%

    No Known Activations