INDEX

Explanations

punctuation marks and formatting indicators within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ISIBLE

-0.18

á»ĵi

-0.16

ekim

-0.15

ãģ£ãģ¨

-0.15

kiem

-0.14

åĪĹ

-0.14

ambil

-0.14

Ð¾Ð½ÑĮ

-0.14

endale

-0.14

POSITIVE LOGITS

dup

0.15

rÃ¥

0.15

HLT

0.14

á»įng

0.14

inos

0.13

idar

0.13

Koh

0.13

Dup

0.13

mam

0.13

avor

0.13

Activations Density 0.002%

punctuation marks and formatting indicators within the text

No Comments

No Known Activations