© 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. 15-LLAMASCOPE-RES-131K
    11. 86960
    Prev
    Next
    INDEX
    Explanations

    terms related to alphabetical and chronological organization

    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
    ÑĢÑĥн
    -0.07
    566
    -0.07
    vre
    -0.06
    linger
    -0.06
     Twist
    -0.06
    леÑĤ
    -0.06
     LIC
    -0.06
    ãĥ¼ãĥ¬
    -0.05
    à¹īà¸Ńà¸Ļ
    -0.05
    OE
    -0.05
    POSITIVE LOGITS
    ScrollIndicator
    0.07
    ramids
    0.07
    uki
    0.07
     latter
    0.07
    彦
    0.07
    insn
    0.06
    hetto
    0.06
    iglia
    0.06
    PEnd
    0.06
    ity
    0.06
    Activations Density 0.002%

    No Known Activations