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. 28-LLAMASCOPE-RES-32K
    6. 29465
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures, particularly in code or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansa
    -0.17
    ostel
    -0.16
    (DialogInterface
    -0.14
    pone
    -0.14
    rame
    -0.14
    almart
    -0.14
    zano
    -0.14
    oload
    -0.13
    argo
    -0.13
    oplayer
    -0.13
    POSITIVE LOGITS
     Dot
    1.58
     dot
    1.58
    Dot
    1.45
    dot
    1.39
    -dot
    1.34
     DOT
    1.27
    _dot
    1.26
     dots
    1.23
    .dot
    1.20
    DOT
    1.15
    Activations Density 0.044%

    No Known Activations