© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87578
    Prev
    Next
    INDEX
    Explanations

    elements related to branding and marketing strategies

    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
    ROLLER
    -0.07
    velt
    -0.07
    ên
    -0.07
    foon
    -0.06
    ologne
    -0.06
    inus
    -0.06
    inned
    -0.06
    inen
    -0.06
     yên
    -0.06
    pora
    -0.06
    POSITIVE LOGITS
     intercept
    0.07
    ency
    0.07
    .scalablytyped
    0.06
     Tribe
    0.06
     Intercept
    0.06
     intercepted
    0.06
     interception
    0.06
    okin
    0.06
    olini
    0.05
    aģı
    0.05
    Activations Density 0.009%

    No Known Activations