© 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. 56046
    Prev
    Next
    INDEX
    Explanations

    mentions of the automotive brand Aston Martin

    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
    .scalablytyped
    -0.07
    utta
    -0.07
    asma
    -0.06
    usal
    -0.06
    uality
    -0.06
    hoot
    -0.06
    addin
    -0.06
     substant
    -0.06
    leen
    -0.06
    cke
    -0.06
    POSITIVE LOGITS
    ingly
    0.07
    orp
    0.07
    .LENGTH
    0.07
    lán
    0.07
    umblr
    0.07
    æŀĿ
    0.07
    cete
    0.07
    l
    0.07
    Č
    0.06
    nant
    0.06
    Activations Density 0.002%

    No Known Activations