INDEX

Explanations

phrases indicating uncertainty or questioning confidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

orem

-0.19

Č

-0.15

\grid

-0.14

Ìģ

-0.14

 DevComponents

-0.13

raquo

-0.13

matchCondition

-0.13

esso

-0.13

 Swinger

-0.12

ModelIndex

-0.12

POSITIVE LOGITS

mouseup

0.15

gorm

0.15

Calibri

0.14

otec

0.14

atro

0.14

alous

0.13

omor

0.12

/etc

0.12

 olsa

0.12

ogh

0.12

Activations Density 1.005%

phrases indicating uncertainty or questioning confidence

No Comments

No Known Activations