INDEX

Explanations

phrases indicating the highest degree of comparison or superlatives

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

strup

-0.19

itler

-0.18

 more

-0.18

.less

-0.17

 Ð±Ð¾Ð»ÐµÐµ

-0.16

alone

-0.16

oled

-0.14

trys

-0.14

ivec

-0.14

 æĽ´

-0.14

POSITIVE LOGITS

 recent

0.23

 likely

0.21

acci

0.21

 pressing

0.19

Recent

0.19

arda

0.19

recent

0.19

-common

0.19

afa

0.18

 important

0.18

Activations Density 0.057%

phrases indicating the highest degree of comparison or superlatives

No Comments

No Known Activations