INDEX

Explanations

punctuation marks indicating pauses or separations in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

entry

-0.16

icut

-0.15

Entry

-0.15

olders

-0.15

 Entry

-0.15

ickers

-0.14

 territorial

-0.14

-scalable

-0.14

UNCH

-0.14

chan

-0.14

POSITIVE LOGITS

0.15

atoria

0.15

fil

0.14

ple

0.14

erner

0.14

.preview

0.14

pep

0.14

amage

0.14

Ã§o

0.14

 Broad

0.14

Activations Density 0.030%

punctuation marks indicating pauses or separations in text

No Comments

No Known Activations