© 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. 9-LLAMASCOPE-RES-131K
    11. 96268
    Prev
    Next
    INDEX
    Explanations

    phrases related to market trends and evaluations within industries

    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
    uby
    -0.07
    erken
    -0.07
    ondo
    -0.06
    ofire
    -0.06
    peq
    -0.06
    dae
    -0.06
    ież
    -0.06
    rů
    -0.06
    AZY
    -0.06
    åħĪçĶŁ
    -0.06
    POSITIVE LOGITS
    _Bool
    0.06
    <typeof
    0.06
     Schmidt
    0.06
    mium
    0.06
     narrative
    0.06
    isol
    0.06
     narratives
    0.06
     primaries
    0.06
     Ult
    0.06
     Indies
    0.06
    Activations Density 0.005%

    No Known Activations