INDEX

Explanations

terms related to institutions and historical figures associated with oppression or inequality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

../../../

-0.17

.Unicode

-0.15

numer

-0.15

Æł

-0.14

stroy

-0.14

áŀ¶

-0.13

ancybox

-0.13

íĴĪ

-0.13

ents

-0.13

POSITIVE LOGITS

erman

0.18

itan

0.17

ier

0.17

/he

0.17

berg

0.15

-water

0.15

efeller

0.15

ermann

0.15

lear

0.15

DTD

0.15

Activations Density 0.767%

terms related to institutions and historical figures associated with oppression or inequality

No Comments

No Known Activations