© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 18-LLAMASCOPE-RES-32K
    6. 24869
    Prev
    Next
    INDEX
    Explanations

    terms related to leaks, water damage, and roofing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eru
    -0.17
    )prepare
    -0.17
     cage
    -0.15
     AVL
    -0.14
    burn
    -0.14
     Cage
    -0.14
    URN
    -0.14
    azzi
    -0.14
    alice
    -0.14
     Sala
    -0.14
    POSITIVE LOGITS
     leak
    0.21
     leaks
    0.21
     foundation
    0.17
     Foundation
    0.17
    crawl
    0.17
    Foundation
    0.16
     Leak
    0.16
     moisture
    0.15
     waterproof
    0.15
     leakage
    0.15
    Activations Density 0.053%

    No Known Activations