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. 20-LLAMASCOPE-RES-32K
    6. 23884
    Prev
    Next
    INDEX
    Explanations

    references to project directories and file paths within a coding or scripting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enberg
    -0.16
    nis
    -0.16
    alle
    -0.15
     aba
    -0.15
    еÑĤÑĮÑģÑı
    -0.15
    razione
    -0.14
    clipboard
    -0.14
    etter
    -0.13
    arrera
    -0.13
    \Console
    -0.13
    POSITIVE LOGITS
    src
    0.32
     src
    0.32
    /src
    0.29
    	src
    0.24
    _src
    0.23
    (src
    0.22
    Src
    0.21
    htdocs
    0.21
    -src
    0.21
     SRC
    0.20
    Activations Density 0.096%

    No Known Activations