© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 21078
    Prev
    Next
    INDEX
    Explanations

    technical terms and functionalities related to data handling and communication protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agt
    -0.15
    ocu
    -0.15
    chandle
    -0.15
    Browsable
    -0.14
    à¸Ľà¸ģà¸Ħรà¸Ńà¸ĩ
    -0.14
    iminal
    -0.14
     Mã
    -0.14
    ovatel
    -0.13
    ylko
    -0.13
    ä¹ĭä¸Ģ
    -0.13
    POSITIVE LOGITS
     future
    0.15
     Normal
    0.14
     Default
    0.14
    acz
    0.14
    _any
    0.14
    Normal
    0.14
     Sez
    0.14
    419
    0.14
    ,default
    0.14
     normal
    0.14
    Activations Density 0.127%

    No Known Activations