INDEX

Explanations

addresses and numerical information related to various entities or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

yna

-0.17

DCF

-0.16

áº¡y

-0.16

è¦³

-0.15

.beh

-0.15

NORMAL

-0.15

laden

-0.14

irket

-0.14

 Freak

-0.13

.boost

-0.13

POSITIVE LOGITS

lic

0.15

plode

0.15

LEC

0.14

 McGregor

0.14

baugh

0.13

emption

0.13

æĻ´

0.13

 Factor

0.13

athon

0.13

pherd

0.13

Activations Density 0.022%

addresses and numerical information related to various entities or locations

No Comments

No Known Activations