INDEX

Explanations

expressions of enthusiasm and excitement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

.scalablytyped

-0.17

umin

-0.17

Ð²Ð¸Ð¶

-0.16

uges

-0.15

chers

-0.15

ings

-0.15

casts

-0.14

ependency

-0.14

 Beer

-0.14

áº¤

-0.14

POSITIVE LOGITS

ibri

0.16

mÄĽ

0.15

.testing

0.15

ener

0.14

elle

0.14

ly

0.14

Vul

0.13

 exciting

0.13

ous

0.13

 excitement

0.13

Activations Density 0.035%

expressions of enthusiasm and excitement

No Comments

No Known Activations