INDEX

Explanations

words indicating alternatives or contrasts

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

alon

-0.15

etag

-0.15

odal

-0.15

.toolbox

-0.14

alysis

-0.14

ĪæĿĥ

-0.14

illisecond

-0.14

.ensure

-0.13

ç¥¨

-0.13

eso

-0.13

POSITIVE LOGITS

NullOr

0.16

pha

0.15

ioc

0.13

oyer

0.13

fried

0.13

ernen

0.13

inha

0.13

 Legal

0.12

Blu

0.12

creen

0.12

Activations Density 0.019%

words indicating alternatives or contrasts

No Comments

No Known Activations