INDEX

Explanations

references to the National Guard and related contexts

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

EdgeInsets

-0.15

oshi

-0.15

Ð¼ÐµÐ¶

-0.15

.mybatisplus

-0.15

 FindObjectOfType

-0.14

å¸¯

-0.14

qed

-0.14

odka

-0.14

æ

-0.14

ockets

-0.14

POSITIVE LOGITS

atum

0.17

ibel

0.15

afen

0.15

sah

0.15

izzy

0.15

ibration

0.15

afs

0.14

ä¹

0.14

sav

0.14

imen

0.14

Activations Density 0.003%

references to the National Guard and related contexts

No Comments

No Known Activations