INDEX

Explanations

phrases that indicate various conditions or qualifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

uky

-0.18

eral

-0.15

imity

-0.15

bart

-0.14

abet

-0.14

contre

-0.14

/share

-0.14

Zum

-0.14

contra

-0.14

.embed

-0.13

POSITIVE LOGITS

thon

0.17

alic

0.16

 Chandler

0.15

ÌĨ

0.15

Ã¶s

0.15

Ã¥n

0.14

å¶

0.14

Ð½Ð¸Ð²

0.14

ules

0.14

Opaque

0.13

Activations Density 0.168%

phrases that indicate various conditions or qualifiers

No Comments

No Known Activations