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. 18-LLAMASCOPE-RES-32K
    6. 16341
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and code structures

    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
    opard
    -0.17
    é¨
    -0.15
    659
    -0.14
     Mans
    -0.14
     Tong
    -0.14
     Archives
    -0.14
    /browse
    -0.13
    .localized
    -0.13
    ath
    -0.13
     declare
    -0.13
    POSITIVE LOGITS
     AST
    0.23
    RuleContext
    0.20
    AST
    0.19
    _AST
    0.19
    .ast
    0.19
     Ast
    0.18
    ast
    0.16
    -tree
    0.16
    tree
    0.16
     Visitor
    0.16
    Activations Density 0.456%

    No Known Activations