INDEX

Explanations

references to the programming context or framework used for testing in the code

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

íĮ

-0.15

ÑıÐ³

-0.14

 Damen

-0.14

agu

-0.14

 isolated

-0.14

ually

-0.14

dum

-0.14

eger

-0.13

iesen

-0.13

POSITIVE LOGITS

PU

0.16

LOSS

0.15

ãĤŃãĥ¥

0.15

ccp

0.15

emmel

0.15

bras

0.14

\brief

0.14

 æ¹

0.14

RectTransform

0.14

ÑĮÐ¸

0.14

Activations Density 0.003%

references to the programming context or framework used for testing in the code

No Comments

No Known Activations