INDEX

Explanations

phrases related to providing advice and recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

amburger

-0.17

Ð½Ð°ÑĩÐµ

-0.17

erde

-0.15

 UNKNOWN

-0.14

eki

-0.14

tae

-0.14

clas

-0.14

-flag

-0.13

ubby

-0.13

elp

-0.13

POSITIVE LOGITS

sters

0.19

ster

0.18

 ìĤ¬íķŃ

0.17

0.14

pered

0.14

orth

0.14

kinson

0.14

rezent

0.14

itt

0.14

ripsi

0.13

Activations Density 0.023%

phrases related to providing advice and recommendations

No Comments

No Known Activations