INDEX

Explanations

verbs and phrases indicating actions or accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÄĻ

-0.16

inue

-0.15

ouch

-0.15

/goto

-0.15

ÑĢÐ°Ð²

-0.14

amar

-0.14

rice

-0.13

Ã¶l

-0.13

Ã¥n

-0.13

unting

-0.13

POSITIVE LOGITS

 exactly

0.95

 precisely

0.76

 Exactly

0.71

Exactly

0.65

 exact

0.48

 genau

0.48

 Ð¸Ð¼ÐµÐ½Ð½Ð¾

0.47

actly

0.41

 prÃ¡vÄĽ

0.38

 Exact

0.36

Activations Density 0.076%

verbs and phrases indicating actions or accomplishments

No Comments

No Known Activations