© 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. 126614
    Prev
    Next
    INDEX
    Explanations

    instances of the word "early" and its variations

    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
    OVE
    -0.07
    ologne
    -0.07
    (strtolower
    -0.07
    AYS
    -0.06
    ubit
    -0.06
    ACY
    -0.06
    arine
    -0.06
    ony
    -0.06
    ogenic
    -0.06
    vů
    -0.06
    POSITIVE LOGITS
    wards
    0.09
    ward
    0.07
    _than
    0.07
    uster
    0.07
    est
    0.07
    zeitig
    0.07
    punkt
    0.06
     verst
    0.06
    WARD
    0.06
    (er
    0.06
    Activations Density 0.011%

    No Known Activations