INDEX

Explanations

phrases indicating uncertainty or lack of knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

alis

-0.16

 none

-0.15

Jab

-0.14

ptive

-0.14

ucus

-0.14

UP

-0.14

 Leader

-0.14

-0.13

uc

-0.13

ucs

-0.13

POSITIVE LOGITS

Ù¾ÛĮ

0.16

icode

0.15

 sque

0.14

RVA

0.14

ikip

0.14

athi

0.14

amation

0.14

ãĤ¹ãĤ«

0.14

ĥ

0.14

.gdx

0.14

Activations Density 0.025%

phrases indicating uncertainty or lack of knowledge

No Comments

No Known Activations