© 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. 17153
    Prev
    Next
    INDEX
    Explanations

    objects or components involved in mechanical or technical processes

    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
    Ùĭ
    -0.06
    ÅĻej
    -0.06
    oles
    -0.06
    ught
    -0.06
    arger
    -0.06
    thon
    -0.06
    igm
    -0.06
    unsch
    -0.06
    ynamic
    -0.06
    isia
    -0.06
    POSITIVE LOGITS
    åıĬåħ¶
    0.07
    UnderTest
    0.07
    \CMS
    0.07
    ãĥ¼ãĥĬ
    0.07
     twice
    0.06
     Twice
    0.06
    wide
    0.06
    584
    0.06
    CCCC
    0.06
    opp
    0.06
    Activations Density 0.033%

    No Known Activations