INDEX

Explanations

phrases indicating exclusions or limits in statements

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

ola

-0.15

ÃĸL

-0.15

ullo

-0.14

ography

-0.14

Î¿ÏĤ

-0.14

æŁľ

-0.14

orge

-0.14

Ã©ro

-0.14

ëŀ

-0.14

POSITIVE LOGITS

illas

0.17

Ð¾Ñħ

0.15

ather

0.15

æ¸¡

0.15

lett

0.15

dued

0.15

iglia

0.14

Ð¼Ð¸Ð½Ð¸

0.14

lee

0.14

LEE

0.14

Activations Density 0.018%

phrases indicating exclusions or limits in statements

No Comments

No Known Activations