© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1544
    Prev
    Next
    INDEX
    Explanations

    HTML or markup elements in text

    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
    bruary
    -0.06
    dates
    -0.06
    ringe
    -0.06
    isin
    -0.05
    illian
    -0.05
    oney
    -0.05
    ptive
    -0.05
    msp
    -0.05
    itted
    -0.05
    ros
    -0.05
    POSITIVE LOGITS
    @nate
    0.07
    ëĦ
    0.07
    ãĥ©ãĤ¤ãĥ³
    0.07
     ÑĤва
    0.07
    oppins
    0.07
    032
    0.07
    ĩ
    0.07
    641
    0.07
    adro
    0.06
    aku
    0.06
    Activations Density 0.001%

    No Known Activations