INDEX

Explanations

references to programs and initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÏģÎ¬

-0.15

LEE

-0.15

posium

-0.14

antino

-0.13

_FRAMEBUFFER

-0.13

aison

-0.13

ãĤ¿ãĥ«

-0.13

_subplot

-0.13

.AutoSizeMode

-0.13

 Ease

-0.13

POSITIVE LOGITS

Ãºp

0.14

enic

0.14

éĬĢ

0.14

 Initi

0.14

Ä¾

0.14

staking

0.14

AttributeValue

0.14

rowad

0.14

-program

0.14

.program

0.14

Activations Density 0.308%

references to programs and initiatives

No Comments

No Known Activations