Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-LLAMASCOPE-RES-32K
    6. 16478
    Prev
    Next
    INDEX
    Explanations

    phrases that ask questions or seek confirmation from the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ercul
    -0.16
    _LSB
    -0.16
    ảm
    -0.15
     EITHER
    -0.15
    ecast
    -0.14
    .Localization
    -0.14
    IVATE
    -0.14
    mani
    -0.14
    rire
    -0.13
    zv
    -0.13
    POSITIVE LOGITS
     guys
    0.28
     remember
    0.25
     ever
    0.25
     remembers
    0.23
    remember
    0.23
     Remember
    0.22
    Remember
    0.21
     sometimes
    0.19
    ever
    0.18
     remembered
    0.18
    Activations Density 0.061%

    No Known Activations