INDEX

Explanations

phrases indicating outcomes or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

¨

-0.16

DNA

-0.15

iman

-0.15

ching

-0.15

DNA

-0.15

inz

-0.14

ota

-0.14

hb

-0.14

ARP

-0.14

OTA

-0.14

POSITIVE LOGITS

wards

0.20

 Stevenson

0.17

ë¬¼ìĿĦ

0.16

aken

0.16

SSION

0.15

 toItem

0.15

ESA

0.15

yl

0.14

eka

0.14

 differently

0.14

Activations Density 0.016%

phrases indicating outcomes or conclusions

No Comments

No Known Activations