© 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. 120494
    Prev
    Next
    INDEX
    Explanations

    references to specific types of products and their availability

    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
     Singles
    -0.06
    adir
    -0.06
    ehler
    -0.06
    quette
    -0.06
    RIES
    -0.06
    inals
    -0.06
    ider
    -0.06
    icap
    -0.06
     {[
    -0.06
    .subscribe
    -0.06
    POSITIVE LOGITS
    Uploaded
    0.07
    ExecutionContext
    0.07
    olo
    0.07
    oppins
    0.07
    prox
    0.07
    çŃĨ
    0.07
    tring
    0.07
    deen
    0.07
    اء
    0.06
     Habit
    0.06
    Activations Density 0.005%

    No Known Activations