INDEX

Explanations

terms related to the immune system and its functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ø¯ÙĨ

-0.17

sten

-0.17

ifo

-0.16

imum

-0.16

ÙĨØ¨

-0.15

innen

-0.15

adero

-0.15

ÙĨ

-0.15

èªŃ

-0.15

ftware

-0.14

POSITIVE LOGITS

awei

0.16

Ã¥de

0.16

0.15

 tired

0.15

 Brick

0.14

StringBuilder

0.14

Aw

0.14

0.13

nis

0.13

Activations Density 0.018%

terms related to the immune system and its functions

No Comments

No Known Activations