© 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. 39182
    Prev
    Next
    INDEX
    Explanations

    instances of the word "had"

    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
    ummings
    -0.07
    onna
    -0.07
    hora
    -0.06
    opa
    -0.06
    ylie
    -0.06
    ented
    -0.06
     âĹĦ
    -0.06
    ãĤŃãĥ³ãĤ°
    -0.06
    ynchronously
    -0.06
    emetery
    -0.06
    POSITIVE LOGITS
    523
    0.06
    ather
    0.06
     fun
    0.06
     initially
    0.06
     charges
    0.06
     Fun
    0.06
     thought
    0.06
    Sharper
    0.06
    323
    0.06
    Ĩ
    0.06
    Activations Density 0.018%

    No Known Activations