INDEX

Explanations

concepts related to manipulation and legitimacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ish

-0.18

ness

-0.18

ald

-0.17

Ø©

-0.17

alar

-0.16

eler

-0.16

ights

-0.16

ight

-0.15

ene

-0.15

POSITIVE LOGITS

ally

0.27

ALLY

0.23

urally

0.17

ately

0.17

atio

0.17

ÑģÑĮ

0.16

ating

0.16

.scalablytyped

0.16

atively

0.15

LOSS

0.15

Activations Density 0.402%

concepts related to manipulation and legitimacy

No Comments

No Known Activations