© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 78378
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ambiguity or vagueness

    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
    enberg
    -0.06
    unal
    -0.06
    enal
    -0.06
     mell
    -0.06
    มà¸Ń
    -0.06
     Watt
    -0.06
    illon
    -0.06
     dikke
    -0.06
    ourg
    -0.05
    :Boolean
    -0.05
    POSITIVE LOGITS
     vague
    0.14
     vag
    0.13
     broad
    0.12
     general
    0.11
     generic
    0.10
    -general
    0.10
    generic
    0.10
     specificity
    0.10
     konkrét
    0.10
    general
    0.10
    Activations Density 0.074%

    No Known Activations