INDEX

Explanations

phrases emphasizing conditional or causal statements involving "that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

us

-0.18

ãģĤãĤĬ

-0.17

ãģĤãĤĭ

-0.16

ised

-0.15

STS

-0.14

spy

-0.14

 Mansion

-0.14

adius

-0.14

iral

-0.14

 Eigen

-0.13

POSITIVE LOGITS

 particular

0.30

ched

0.30

/th

0.28

 same

0.28

zelf

0.26

 SAME

0.24

 PARTICULAR

0.23

 Ð¶Ðµ

0.22

-ÑĤÐ¾

0.21

gene

0.18

Activations Density 0.180%

phrases emphasizing conditional or causal statements involving "that."

No Comments

No Known Activations