INDEX

Explanations

punctuation marks and their usage in 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

hton

-0.17

arians

-0.15

ÙĦÙħÙĩ

-0.15

heid

-0.15

hta

-0.14

ZN

-0.14

ends

-0.14

endo

-0.14

.ASCII

-0.14

UFF

-0.14

POSITIVE LOGITS

aben

0.16

osite

0.15

.getWriter

0.15

 Greens

0.14

icket

0.14

Mob

0.14

zeit

0.14

imu

0.14

etr

0.14

ieg

0.14

Activations Density 0.044%

punctuation marks and their usage in the text

No Comments

No Known Activations