INDEX

Explanations

phrases indicating recognition or reputation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.18

ackson

-0.15

uros

-0.15

ertz

-0.14

Ø´ØªÙĩ

-0.14

ych

-0.14

spot

-0.14

NR

-0.14

rix

-0.14

Ð°Ð½Ð¾Ð²

-0.14

POSITIVE LOGITS

 thÃ¡c

0.15

Æ¡i

0.15

 Gaul

0.15

zig

0.14

ifi

0.14

 IOCTL

0.14

.nlm

0.14

_LED

0.14

awai

0.13

opi

0.13

Activations Density 0.008%

phrases indicating recognition or reputation

No Comments

No Known Activations