INDEX

Explanations

phrases related to missing events or opportunities

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

ifar

-0.16

Ð¾ÑģÑĤÐ°ÑĤ

-0.16

_unref

-0.15

_IL

-0.15

 éł

-0.15

 Magnet

-0.14

Monkey

-0.14

Ú¯ÙĪ

-0.14

Markers

-0.14

utin

-0.14

POSITIVE LOGITS

 miss

1.02

miss

1.01

 missed

0.95

 misses

0.93

 Miss

0.92

 missing

0.92

Miss

0.86

MISS

0.81

 MISS

0.80

missing

0.78

Activations Density 0.234%

phrases related to missing events or opportunities

No Comments

No Known Activations