INDEX

Explanations

terms related to professionalism and expertise

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

OLEAN

-0.16

 MethodInfo

-0.15

 Metro

-0.15

Ler

-0.15

.metro

-0.14

bakan

-0.14

ipers

-0.14

 generations

-0.14

exp

-0.14

fef

-0.14

POSITIVE LOGITS

oug

0.18

/icons

0.15

.Transactional

0.15

terdam

0.15

ERSHEY

0.14

 Graham

0.14

tparam

0.14

fÃ¼hrt

0.14

ourke

0.14

uder

0.14

Activations Density 0.063%

terms related to professionalism and expertise

No Comments

No Known Activations