INDEX

Explanations

specific programming or coding-related terminology and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

bere

-0.15

arend

-0.15

 bere

-0.15

cola

-0.14

 dispon

-0.14

urt

-0.13

 ÙħØ±Ú©

-0.13

umo

-0.13

burger

-0.13

hik

-0.13

POSITIVE LOGITS

to

0.18

for

0.15

 Vander

0.15

 unto

0.14

deaux

0.14

ì§¸

0.14

orrect

0.14

Ã¥r

0.14

lias

0.14

of

0.13

Activations Density 0.034%

specific programming or coding-related terminology and structures

No Comments

No Known Activations