© 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. 15-LLAMASCOPE-RES-131K
    11. 103524
    Prev
    Next
    INDEX
    Explanations

    phrases indicating origin or source

    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
    _ASSUME
    -0.07
     xung
    -0.07
    frei
    -0.07
    eyle
    -0.07
    /Instruction
    -0.07
    æľ¬å½ĵ
    -0.07
    alte
    -0.06
    alama
    -0.06
    rts
    -0.06
     ÙħستÙĤ
    -0.06
    POSITIVE LOGITS
     previous
    0.08
     previously
    0.06
    previous
    0.06
     Else
    0.06
     Previous
    0.06
    else
    0.06
    Previous
    0.06
    loo
    0.05
    err
    0.05
    ATA
    0.05
    Activations Density 0.011%

    No Known Activations