© 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. 29763
    Prev
    Next
    INDEX
    Explanations

    dates formatted as month and day

    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
    phans
    -0.07
    #ad
    -0.07
    ùa
    -0.07
    Liver
    -0.07
    _ci
    -0.07
    qc
    -0.06
    roscope
    -0.06
    ovna
    -0.06
    .Dial
    -0.06
    оÑģÑĮ
    -0.06
    POSITIVE LOGITS
    itzer
    0.06
    ainer
    0.06
     Pill
    0.06
     Rai
    0.05
    aling
    0.05
     often
    0.05
    PEC
    0.05
     Abed
    0.05
     scre
    0.05
     Gron
    0.05
    Activations Density 0.003%

    No Known Activations