INDEX

Explanations

words related to action, consequences, and conditions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

atte

-0.18

VS

-0.16

vs

-0.16

 Sutton

-0.15

 underlying

-0.15

ACP

-0.14

 Terr

-0.14

Ã¶h

-0.14

RDD

-0.13

 poil

-0.13

POSITIVE LOGITS

 ÙģØ¥ÙĨ

0.16

èĢĮ

0.15

ozo

0.15

hta

0.15

 èĢĮ

0.14

nect

0.14

 Swing

0.14

à¹ģà¸¥

0.14

.netbeans

0.13

Ð¿Ð¸Ð¾Ð½

0.13

Activations Density 0.347%

words related to action, consequences, and conditions in various contexts

No Comments

No Known Activations