© 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. 106657
    Prev
    Next
    INDEX
    Explanations

    sections of code or programming language syntax

    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
    phinx
    -0.07
    ngine
    -0.07
    ноÑģи
    -0.07
    SFML
    -0.07
    ẻ
    -0.07
    anyak
    -0.06
    ãĤªãĥ³
    -0.06
    izz
    -0.06
     Beard
    -0.06
    į¼
    -0.06
    POSITIVE LOGITS
     public
    0.09
    public
    0.07
    	public
    0.07
    Åį
    0.07
    ÙĥÙħ
    0.06
     público
    0.06
    aran
    0.06
    yun
    0.06
    ÅĻes
    0.06
    aul
    0.06
    Activations Density 0.010%

    No Known Activations