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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 10851
    Prev
    Next
    INDEX
    Explanations

    keywords and annotations related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropp
    -0.18
    isin
    -0.16
    eds
    -0.15
     Método
    -0.14
    esa
    -0.14
     Throws
    -0.14
    ãĥ¯ãĥ¼
    -0.14
    Soup
    -0.13
     dostan
    -0.13
    ico
    -0.13
    POSITIVE LOGITS
     class
    0.32
    class
    0.28
    public
    0.24
    @interface
    0.24
     public
    0.21
     abstract
    0.20
     final
    0.20
    final
    0.19
    @Slf
    0.19
    	class
    0.17
    Activations Density 0.013%

    No Known Activations