INDEX

Explanations

words with the prefix "re-" indicating repetition or return

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

oretical

-0.26

-0.25

vol

-0.25

ÑħÐ¾Ð´

-0.24

-0.23

gether

-0.22

ories

-0.22

un

-0.21

POSITIVE LOGITS

ductive

0.26

der

0.24

duct

0.24

too

0.23

semb

0.22

straints

0.22

data

0.21

word

0.20

sem

0.20

develop

0.20

Activations Density 0.020%

words with the prefix "re-" indicating repetition or return

No Comments

No Known Activations