© 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. 128175
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between concepts or entities

    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
    azen
    -0.07
    illez
    -0.07
     Verd
    -0.06
    regor
    -0.06
    otime
    -0.06
    Bounding
    -0.06
    faction
    -0.06
    fea
    -0.06
    FI
    -0.06
    elson
    -0.06
    POSITIVE LOGITS
    èľľ
    0.07
    owi
    0.06
    ê¶ģ
    0.06
     exploitation
    0.06
    via
    0.06
     nhau
    0.06
     alike
    0.06
    anter
    0.06
    asca
    0.06
    ml
    0.06
    Activations Density 0.098%

    No Known Activations