INDEX

Explanations

occurrences of the word "de" and its various forms in different contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

äºº

-0.16

nyder

-0.15

ildren

-0.15

arger

-0.15

rots

-0.14

ä¸Ģçº§

-0.14

iveau

-0.14

(*(

-0.14

vang

-0.14

oric

-0.13

POSITIVE LOGITS

 forma

0.19

 manera

0.18

way

0.17

 acuerdo

0.17

str

0.16

tt

0.16

utex

0.15

ways

0.15

bo

0.15

amb

0.15

Activations Density 0.022%

occurrences of the word "de" and its various forms in different contexts

No Known Activations