INDEX

Explanations

phrases that indicate the viewer's engagement or interaction with content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ald

-0.17

bei

-0.15

imeo

-0.14

leys

-0.14

rgan

-0.14

ernel

-0.14

 defaultManager

-0.14

etails

-0.14

prompt

-0.13

 Locker

-0.13

POSITIVE LOGITS

utz

0.19

ormsg

0.18

0.16

ÙĨÚ¯ÛĮ

0.16

ache

0.15

aliz

0.14

ODY

0.14

etz

0.14

chop

0.14

erif

0.14

Activations Density 0.074%

phrases that indicate the viewer's engagement or interaction with content

No Comments

No Known Activations