INDEX

Explanations

phrases indicating expectations or promises related to events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ooth

-0.18

:CGRect

-0.17

Ð·Ð´

-0.17

ÏĦÎ·

-0.15

.getAs

-0.15

ŀ

-0.15

inidad

-0.14

Ð°ÑĤÐºÐ¸

-0.14

prav

-0.14

_continuous

-0.14

POSITIVE LOGITS

Ø¯ÙĪ

0.16

à¸¶à¸ģ

0.16

 Doch

0.14

 Berg

0.13

atti

0.13

enders

0.13

 Battlefield

0.13

Activations Density 0.145%

phrases indicating expectations or promises related to events or situations

No Comments

No Known Activations