INDEX

Explanations

phrases that indicate the existence or status of a subject, particularly forms of the verb "to be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rw

-0.15

rtl

-0.15

edly

-0.14

unge

-0.14

è¿

-0.14

rank

-0.14

izon

-0.14

omorphic

-0.13

.inst

-0.13

spoken

-0.13

POSITIVE LOGITS

bay

0.16

éĢŁ

0.16

IONS

0.14

ProgressHUD

0.14

llu

0.14

.qt

0.14

 bail

0.14

angu

0.14

YTE

0.13

Activations Density 0.019%

phrases that indicate the existence or status of a subject, particularly forms of the verb "to be."

No Comments

No Known Activations