INDEX

Explanations

phrases indicating quantity or numerical relationships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

declspec

-0.16

ANE

-0.15

dan

-0.15

xac

-0.14

 McCl

-0.14

Ty

-0.14

iran

-0.13

 vice

-0.13

á»©

-0.13

 Ortiz

-0.13

POSITIVE LOGITS

0.16

ecut

0.15

fragistics

0.15

rollo

0.15

nings

0.15

Ð½Ð¾Ð¶

0.15

egend

0.14

adt

0.14

ÑĨÐµÑĢ

0.13

Looper

0.13

Activations Density 0.015%

phrases indicating quantity or numerical relationships

No Comments

No Known Activations