INDEX

Explanations

instances of the word "significant" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ject

-0.20

erman

-0.19

bage

-0.16

cri

-0.15

ÑĩÐµÑĢ

-0.15

å¼ı

-0.15

ermann

-0.15

oom

-0.15

ãģĦãģĨ

-0.14

igue

-0.14

POSITIVE LOGITS

 portions

0.23

 portion

0.22

/sign

0.21

 amount

0.20

 amounts

0.20

ately

0.19

 enough

0.19

;y

0.19

amount

0.19

ity

0.19

Activations Density 0.034%

instances of the word "significant" and its variations

No Comments

No Known Activations