INDEX

Explanations

phrases indicating restrictions or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

endency

-0.16

EncodingException

-0.15

åĿĬ

-0.15

Ø¯Ø§ÙĨ

-0.14

.Generated

-0.14

senal

-0.14

colo

-0.13

åĤ¬

-0.13

kas

-0.13

allback

-0.13

POSITIVE LOGITS

ings

0.22

lessly

0.19

ActionCreators

0.19

less

0.18

edly

0.17

aries

0.17

-bound

0.17

tight

0.16

ervo

0.16

bound

0.16

Activations Density 0.029%

phrases indicating restrictions or limitations

No Comments

No Known Activations