© 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. 17-LLAMASCOPE-RES-131K
    11. 92922
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or association with a specific context

    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
    ly
    -0.07
    allet
    -0.07
    ane
    -0.07
    per
    -0.06
    aring
    -0.06
    ncy
    -0.06
     Pascal
    -0.06
    irket
    -0.06
    urse
    -0.06
    peria
    -0.06
    POSITIVE LOGITS
    voor
    0.08
    ington
    0.07
    368
    0.07
    inati
    0.07
    onet
    0.07
    366
    0.07
    orthand
    0.06
    otto
    0.06
    olla
    0.06
    ác
    0.06
    Activations Density 0.004%

    No Known Activations