INDEX

Explanations

terms and phrases that refer to specific topics or categories within a broader context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

mina

-0.18

acket

-0.17

alim

-0.16

 ãĥ¡

-0.15

ÑıÐº

-0.15

áº¡p

-0.15

imat

-0.15

strconv

-0.15

 Ø®Ø·

-0.14

ÑĸÑģÑĤ

-0.14

POSITIVE LOGITS

rog

0.16

ity

0.16

ities

0.15

appoint

0.14

vanced

0.14

æŁ´

0.14

/owl

0.14

ihad

0.14

 thÃ¹

0.14

AtPath

0.14

Activations Density 0.008%

terms and phrases that refer to specific topics or categories within a broader context

No Comments

No Known Activations