INDEX

Explanations

phrases related to clarity and transparency

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

utin

-0.17

dispatch

-0.16

alars

-0.15

ponible

-0.14

tuk

-0.14

á»ķ

-0.14

sert

-0.14

ToFront

-0.14

declare

-0.13

-validate

-0.13

POSITIVE LOGITS

 æħ

0.16

Ð¸ÑĢÐ¾Ð²

0.15

.TYPE

0.14

.TestTools

0.14

iams

0.14

\application

0.14

 Milli

0.14

 ÙħØ§ÙĨØ¯

0.14

anson

0.14

 ÙĪØ§ØŃ

0.14

Activations Density 0.288%

phrases related to clarity and transparency

No Comments

No Known Activations

phrases related to clarity and transparency

No Comments

No Known Activations