INDEX

Explanations

references to significant historical events and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

TECT

-0.17

FIXME

-0.15

ãĤ¦ãĥĪ

-0.14

dden

-0.14

ITY

-0.14

vent

-0.14

sit

-0.14

çļĦå°ı

-0.13

venture

-0.13

Ð½ÑĸÐ²ÐµÑĢ

-0.13

POSITIVE LOGITS

-scale

0.24

 Britain

0.18

 endian

0.18

uja

0.18

/big

0.17

-sized

0.17

/small

0.17

 Ã¶lÃ§Ã¼de

0.17

obb

0.17

 powers

0.16

Activations Density 0.043%

references to significant historical events and figures

No Comments

No Known Activations

references to significant historical events and figures

No Comments

No Known Activations