INDEX

Explanations

punctuation marks that indicate sentence boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ftime

-0.17

ediator

-0.15

ÅĪ

-0.15

ayload

-0.14

zel

-0.14

èĪĹ

-0.14

ividad

-0.14

Ð¼ÐµÐ¶

-0.14

plode

-0.14

issippi

-0.14

POSITIVE LOGITS

etal

0.16

ers

0.16

 Wolver

0.15

 Emer

0.15

Featured

0.14

UV

0.14

Emer

0.14

emoth

0.14

 Williamson

0.14

Activations Density 0.008%

punctuation marks that indicate sentence boundaries

No Comments

No Known Activations