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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 14363
    Prev
    Next
    INDEX
    Explanations

    patterns in structured data or code-like syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansom
    -0.16
    /or
    -0.15
     ↵
    -0.14
    ilateral
    -0.14
    ,
    -0.14
    /no
    -0.14
    etti
    -0.14
    bie
    -0.14
    ovel
    -0.14
    iki
    -0.14
    POSITIVE LOGITS
    yre
    0.18
    	 
    0.17
    ↵    ↵    ↵
    0.16
    ↵    ↵
    0.16
    ../../../
    0.15
    reopen
    0.15
    forth
    0.14
     mastur
    0.14
     ^↵
    0.14
     undermin
    0.14
    Activations Density 0.170%

    No Known Activations