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. 16843
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements

    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
    abler
    -0.15
    ys
    -0.15
     Duncan
    -0.15
    ÑĸнÑĮ
    -0.15
    £¨
    -0.14
    uzzy
    -0.14
    ierz
    -0.14
    rouch
    -0.14
    itz
    -0.14
    าศ
    -0.14
    POSITIVE LOGITS
    625
    0.30
    875
    0.28
    125
    0.27
    375
    0.26
     quarter
    0.23
    25
    0.21
    250
    0.21
    75
    0.21
     Quarter
    0.20
    062
    0.20
    Activations Density 0.128%

    No Known Activations