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. 31-LLAMASCOPE-RES-32K
    6. 2031
    Prev
    Next
    INDEX
    Explanations

    sentences related to formal announcements or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deaux
    -0.16
    atural
    -0.12
    StackNavigator
    -0.12
    assertCount
    -0.11
    쳤ëĭ¤
    -0.11
    ê´
    -0.10
    μοÏģ
    -0.10
    ÑĢÑĸд
    -0.10
    алов
    -0.10
     removeFromSuperview
    -0.10
    POSITIVE LOGITS
     start
    0.99
     starts
    0.91
     begin
    0.88
     starting
    0.87
     beginning
    0.85
    -start
    0.82
    start
    0.82
     begins
    0.81
     Start
    0.80
    å¼Ģå§ĭ
    0.79
    Activations Density 1.533%

    No Known Activations