INDEX

Explanations

terms related to growth and increase in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÄĽk

-0.15

kee

-0.15

 twice

-0.14

Ø²ÙĦ

-0.14

 varying

-0.14

 upfront

-0.14

orst

-0.14

 lasting

-0.14

vice

-0.14

uisse

-0.14

POSITIVE LOGITS

rapid

0.25

Fast

0.24

 Rapid

0.24

 fast

0.24

 year

0.23

 rapid

0.23

 rapidly

0.23

 fastest

0.22

 Fast

0.22

-fast

0.22

Activations Density 0.171%

terms related to growth and increase in various contexts

No Comments

No Known Activations