INDEX

Explanations

mentions of lawsuits

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

unker

-0.17

Ð°ÑĤÐµÐ»ÑĮÐ½ÑĭÑħ

-0.14

 nÄĥ

-0.14

ÄĻk

-0.13

isty

-0.13

 bicy

-0.13

ulton

-0.13

 Ð²Ð·

-0.13

 Naked

-0.13

chai

-0.13

POSITIVE LOGITS

edback

0.17

-ending

0.16

æķ·

0.15

enses

0.15

_PE

0.15

idal

0.15

ioctl

0.15

quil

0.14

ILE

0.14

.jupiter

0.14

Activations Density 0.005%

mentions of lawsuits

No Comments

No Known Activations