© 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. 74604
    Prev
    Next
    INDEX
    Explanations

    reflections on personal experiences and decisions

    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
    å¿ľ
    -0.09
    prit
    -0.07
    ovna
    -0.06
    atables
    -0.06
    bast
    -0.06
    orida
    -0.06
    VERT
    -0.06
     Premium
    -0.06
     ing
    -0.06
    rina
    -0.06
    POSITIVE LOGITS
     hindsight
    0.08
    indsight
    0.07
     Trades
    0.07
     regrets
    0.06
    ặp
    0.06
     knowing
    0.06
     TRADE
    0.06
    _hdl
    0.06
     wouldn
    0.06
     differently
    0.06
    Activations Density 0.026%

    No Known Activations