© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4034
    Prev
    Next
    INDEX
    Explanations

    interactions and relationships between different elements, often in the context of food and exhibitions

    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
    ška
    -0.07
    afil
    -0.07
    rk
    -0.07
    ìĸij
    -0.07
    clin
    -0.07
    igg
    -0.07
    ukes
    -0.07
    à¹Ĥม
    -0.06
     WithEvents
    -0.06
    åIJ¹
    -0.06
    POSITIVE LOGITS
     combinations
    0.08
    çµĦ
    0.08
     combos
    0.07
     complimentary
    0.07
     mixing
    0.07
     pairing
    0.07
     pair
    0.07
     pairs
    0.06
     oppos
    0.06
    ç»Ħ
    0.06
    Activations Density 0.022%

    No Known Activations