INDEX

Explanations

punctuation marks and sentence endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

↵

-0.19

-0.18

-0.17

âĢ¦

-0.16

–

-0.16

anz

-0.16

My

-0.16

 Vulcan

-0.15

POSITIVE LOGITS

íĨłíĨł

0.16

chandle

0.16

Ø§ÙħÙĩ

0.16

ï»¿using

0.16

.fx

0.15

mae

0.15

OWN

0.15

mojom

0.15

Ð¢Ðŀ

0.15

Opcode

0.15

Activations Density 0.108%

punctuation marks and sentence endings

No Comments

No Known Activations