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. 29-LLAMASCOPE-RES-32K
    6. 17447
    Prev
    Next
    INDEX
    Explanations

    themes related to darkness and obscurity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elps
    -0.15
    ogue
    -0.15
     Deb
    -0.14
     Destiny
    -0.14
     Duy
    -0.14
    à¹īà¸ĩ
    -0.14
    ê·¹
    -0.13
    odb
    -0.13
    leur
    -0.13
    анÑĤ
    -0.13
    POSITIVE LOGITS
     dark
    0.69
     darkness
    0.63
    dark
    0.61
     DARK
    0.60
    -dark
    0.59
    Dark
    0.57
     Dark
    0.56
     pitch
    0.54
     Darkness
    0.49
    .dark
    0.48
    Activations Density 0.125%

    No Known Activations