INDEX

Explanations

punctuation marks and their associated patterns

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

.TestTools

-0.16

byss

-0.15

nero

-0.15

affen

-0.14

nist

-0.14

helm

-0.14

 Ù¾Ø§ÛĮ

-0.14

Ã¢y

-0.14

edList

-0.14

ÐĲÑĢÑħÑĸÐ²

-0.14

POSITIVE LOGITS

QUOTE

0.18

quote

0.17

Quote

0.16

eger

0.15

 quote

0.15

(Runtime

0.14

:↵

0.14

wr

0.14

 Quote

0.14

aly

0.14

Activations Density 0.090%

punctuation marks and their associated patterns

No Comments

No Known Activations