INDEX

Explanations

titles or names of companies and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

abox

-0.19

inde

-0.16

KeyEvent

-0.15

-0.14

ongyang

-0.14

imson

-0.14

gom

-0.14

íĤ¹

-0.14

 Hector

-0.14

Ø¨Ø±

-0.13

POSITIVE LOGITS

uitka

0.16

neh

0.15

umas

0.15

Æ°á»Ľ

0.15

ISTRY

0.14

 Zucker

0.14

_FORCE

0.14

å½©

0.14

ÑģÑĤÑĮ

0.14

URRENT

0.13

Activations Density 0.030%

titles or names of companies and organizations

No Comments

No Known Activations