INDEX

Explanations

sentences that convey varying levels of confidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ardon

-0.16

ubu

-0.16

Configurer

-0.15

 WaitForSeconds

-0.15

essler

-0.14

Mahon

-0.14

linger

-0.14

ä¼¦

-0.14

vester

-0.14

ependency

-0.14

POSITIVE LOGITS

/conf

0.20

 confidence

0.17

 Confidence

0.17

ki

0.17

wart

0.16

Ki

0.15

Ki

0.15

 assured

0.14

nt

0.14

Activations Density 0.011%

sentences that convey varying levels of confidence

No Comments

No Known Activations