INDEX

Explanations

terms related to peripheral conditions or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oho

-0.16

å¤

-0.16

ÎµÏģÏĮ

-0.15

DMI

-0.15

íĦ°

-0.15

ftar

-0.15

Ã¸y

-0.15

gle

-0.14

ingt

-0.14

edo

-0.14

POSITIVE LOGITS

0.16

 Civil

0.15

 Railway

0.15

clusive

0.14

adal

0.14

 SaÄŁ

0.14

WORD

0.14

 keyword

0.14

pav

0.14

 Human

0.13

Activations Density 0.005%

terms related to peripheral conditions or issues

No Comments

No Known Activations