© 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. 30-LLAMASCOPE-RES-32K
    11. 13565
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     firstly
    -0.25
     Firstly
    -0.22
    ãģ¾ãģļ
    -0.19
    :
    -0.19
    either
    -0.19
     either
    -0.18
     EITHER
    -0.18
     Either
    -0.17
     BOTH
    -0.17
    æĹ¢
    -0.17
    POSITIVE LOGITS
     consequ
    0.38
     subsequent
    0.34
     consequently
    0.31
     subsequently
    0.30
     associated
    0.29
     importantly
    0.29
     corresponding
    0.29
     accompanying
    0.28
     overall
    0.26
     resulting
    0.26
    Activations Density 1.646%

    No Known Activations