© 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. 30054
    Prev
    Next
    INDEX
    Explanations

    instances of similarity or repetition in characteristics or qualities

    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
    inen
    -0.06
     correspond
    -0.06
     jag
    -0.05
    j
    -0.05
     separate
    -0.05
    etter
    -0.05
    elo
    -0.05
    eron
    -0.05
    jac
    -0.05
    ewe
    -0.05
    POSITIVE LOGITS
     identical
    0.16
     uniform
    0.15
     ident
    0.13
    缸åIJĮ
    0.13
    Uniform
    0.13
    uniform
    0.12
     Ident
    0.12
     Uniform
    0.12
     alike
    0.11
    ident
    0.11
    Activations Density 0.059%

    No Known Activations