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. 24107
    Prev
    Next
    INDEX
    Explanations

    technical code and programming constructs

    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
    eum
    -0.15
    Ø´Ùĩ
    -0.15
    _slider
    -0.14
    idge
    -0.14
    asl
    -0.14
    obot
    -0.14
    fallback
    -0.14
    Robin
    -0.13
    dart
    -0.13
     Locator
    -0.13
    POSITIVE LOGITS
     edit
    0.31
     Edit
    0.26
    edit
    0.26
     editing
    0.26
    Edit
    0.26
    _edit
    0.25
     EDIT
    0.25
    .edit
    0.25
     íݸì§ij
    0.23
    -edit
    0.23
    Activations Density 0.152%

    No Known Activations