INDEX

Explanations

references to emotional impacts and significant historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

bjerg

-0.18

keh

-0.16

heel

-0.15

rava

-0.14

aku

-0.14

ZY

-0.14

noinspection

-0.14

ihil

-0.14

onen

-0.14

Rum

-0.14

POSITIVE LOGITS

uan

0.15

íĴĪ

0.14

£

0.14

ê°Ŀ

0.14

 Ð¡ÑĤÑĢÐ°Ð½Ð°

0.14

Ð°Ñĩ

0.14

abcdefghijkl

0.14

/address

0.14

sn

0.14

ÙĦÙĤ

0.14

Activations Density 0.011%

references to emotional impacts and significant historical events

No Comments

No Known Activations