INDEX

Explanations

phrases indicating ongoing or repeated actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ConnectionFactory

-0.16

Mono

-0.15

rew

-0.15

aget

-0.14

LayoutManager

-0.14

vie

-0.14

aban

-0.13

 mono

-0.13

olland

-0.13

ron

-0.13

POSITIVE LOGITS

ìĤ¬íķŃ

0.15

mÃŃ

0.14

_unregister

0.14

cx

0.14

ooter

0.13

å²³

0.13

 ìĤ¬íķŃ

0.13

.pref

0.13

ORK

0.13

ergy

0.13

Activations Density 0.018%

phrases indicating ongoing or repeated actions or states

No Comments

No Known Activations