INDEX

Explanations

phrases indicating uncertainty or lack of seriousness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

stantiate

-0.18

iber

-0.15

aily

-0.15

ught

-0.15

 Ling

-0.14

bye

-0.14

ìº

-0.14

yn

-0.14

POSITIVE LOGITS

 strategy

0.17

 categorical

0.16

ZO

0.16

strategy

0.16

veis

0.15

oÅ¡

0.15

 concentration

0.15

 physical

0.14

 location

0.14

à¤Ī

0.14

Activations Density 0.009%

phrases indicating uncertainty or lack of seriousness

No Comments

No Known Activations