INDEX

Explanations

references to statements and remarks made by individuals

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

-0.17

jian

-0.17

ialis

-0.17

Margins

-0.17

uida

-0.16

 Harding

-0.15

olph

-0.15

ush

-0.15

loom

-0.14

ÐºÐ¸Ð½

-0.14

POSITIVE LOGITS

(#)

0.16

abol

0.16

æĳĺ

0.15

utilus

0.15

ritz

0.14

neider

0.14

abay

0.14

orde

0.14

semicolon

0.14

atoon

0.13

Activations Density 0.027%

references to statements and remarks made by individuals

No Comments

No Known Activations