INDEX

Explanations

verbs indicating actions or occurrences that impact outcomes

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

unner

-0.15

ime

-0.15

-part

-0.15

BOR

-0.15

bor

-0.15

bor

-0.15

 partner

-0.14

ropdown

-0.14

plier

-0.14

 Matters

-0.14

POSITIVE LOGITS

ycastle

0.16

Ä¢

0.15

YD

0.15

storybook

0.14

ctp

0.14

elly

0.13

ingt

0.13

moth

0.13

 LOSS

0.13

awaii

0.13

Activations Density 0.365%

verbs indicating actions or occurrences that impact outcomes

No Comments

No Known Activations