© 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. 55991
    Prev
    Next
    INDEX
    Explanations

    references to heirs or lineage

    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
    eer
    -0.07
    oto
    -0.07
    tainment
    -0.07
    OTO
    -0.07
    anton
    -0.06
     haut
    -0.06
    /email
    -0.06
    urator
    -0.06
    lx
    -0.06
    ylvania
    -0.06
    POSITIVE LOGITS
    loom
    0.11
    ship
    0.10
     apparent
    0.08
    locks
    0.07
    duk
    0.07
    ighth
    0.07
    atatype
    0.07
    unsafe
    0.07
    imate
    0.07
    iffs
    0.07
    Activations Density 0.002%

    No Known Activations