© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 13770
    Prev
    Next
    INDEX
    Explanations

    content related to data management and organization challenges

    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
    undy
    -0.16
    оÑĤов
    -0.14
    ymax
    -0.14
    ãĥ¼ãĥĨ
    -0.14
    ÑĢеб
    -0.14
    ิà¸ĩ
    -0.14
    sing
    -0.13
    iena
    -0.13
    ð
    -0.13
    ugal
    -0.13
    POSITIVE LOGITS
     solution
    0.59
     remedy
    0.57
    è§£åĨ³
    0.51
    solution
    0.50
    Solution
    0.50
     Solution
    0.48
     SOLUTION
    0.48
     solutions
    0.47
     íķ´ê²°
    0.47
     remedies
    0.45
    Activations Density 0.386%

    No Known Activations