© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41094
    Prev
    Next
    INDEX
    Explanations

    references to online directories and ticket-related services

    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
    (
    -0.07
    via
    -0.06
     (
    -0.05
    uma
    -0.05
     
    -0.05
    alt
    -0.05
     Pod
    -0.05
    emble
    -0.05
    C
    -0.05
    _
    -0.05
    POSITIVE LOGITS
    ToObject
    0.09
    DDL
    0.09
    ãĥ¼ãĥĦ
    0.08
    #__
    0.08
     Köy
    0.08
    .foundation
    0.08
    Refs
    0.08
    ìĬĪ
    0.08
    enaire
    0.08
    ((__
    0.08
    Activations Density 0.007%

    No Known Activations