© 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. 13-LLAMASCOPE-RES-32K
    11. 16051
    Prev
    Next
    INDEX
    Explanations

    various HTML and XML-related tags and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stin
    -0.14
    mania
    -0.13
    rog
    -0.13
     Pun
    -0.13
     Rough
    -0.13
    597
    -0.13
     ÃĤ
    -0.13
    .community
    -0.13
     transported
    -0.13
     Necessary
    -0.13
    POSITIVE LOGITS
    .dtd
    0.18
    ież
    0.15
    .DOM
    0.15
    .UIManager
    0.14
    brtc
    0.14
    ilda
    0.14
    è²´
    0.14
    dana
    0.14
     Ukra
    0.13
    èĤ¯å®ļ
    0.13
    Activations Density 0.001%

    No Known Activations