INDEX

Explanations

phrases related to news updates and newsletters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 brig

-0.16

 radio

-0.15

nell

-0.14

rl

-0.14

åĢ

-0.14

Ann

-0.14

 Works

-0.14

 radi

-0.14

brick

-0.13

 works

-0.13

POSITIVE LOGITS

esson

0.15

.Subscribe

0.15

AppDelegate

0.15

engkap

0.15

iosa

0.15

uci

0.15

.pg

0.15

breaking

0.14

Coverage

0.14

íĳ¸

0.14

Activations Density 0.060%

phrases related to news updates and newsletters

No Comments

No Known Activations