© 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. 31-LLAMASCOPE-RES-32K
    11. 7142
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and software functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     USB
    -0.17
    USB
    -0.16
     Pac
    -0.16
     Manhattan
    -0.16
     Sat
    -0.15
     Benton
    -0.15
     Wed
    -0.15
     Blaze
    -0.14
     PAC
    -0.14
     Molly
    -0.14
    POSITIVE LOGITS
     TSRMLS
    0.38
     zend
    0.34
    zend
    0.30
     ZEND
    0.30
     Php
    0.24
     php
    0.24
     PHP
    0.24
     Zend
    0.24
    _php
    0.23
    Php
    0.23
    Activations Density 0.008%

    No Known Activations