Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5377
    Prev
    Next
    INDEX
    Explanations

    programming constructs and variable declarations

    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
     âĸij
    -0.06
    rir
    -0.06
    åºĶ
    -0.06
    rh
    -0.06
    алÑĮне
    -0.06
     onBind
    -0.06
    .Pow
    -0.06
     authorised
    -0.06
    ccione
    -0.06
    binding
    -0.06
    POSITIVE LOGITS
     protected
    0.13
     private
    0.12
    protected
    0.11
     Protected
    0.10
    private
    0.10
    	protected
    0.08
    (private
    0.07
    	private
    0.07
     Private
    0.07
     PRIVATE
    0.07
    Activations Density 0.003%

    No Known Activations