INDEX

Explanations

phrases that indicate requirements, actions, or specific task details related to safety, services, and financial terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.15

 dist

-0.14

rev

-0.14

ylim

-0.14

xfb

-0.13

gre

-0.13

rg

-0.13

YST

-0.13

 prot

-0.13

ivec

-0.13

POSITIVE LOGITS

atica

0.17

llib

0.16

assa

0.15

ibbon

0.15

rupt

0.15

iger

0.14

 Lunch

0.14

 meiden

0.14

ubuntu

0.14

ichert

0.13

Activations Density 0.297%

phrases that indicate requirements, actions, or specific task details related to safety, services, and financial terms

No Comments

No Known Activations