INDEX

Explanations

expressions of frustration or disbelief

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Hmm

-0.17

ervers

-0.17

 Oops

-0.16

Damn

-0.15

Yep

-0.15

acman

-0.15

Hmm

-0.15

 iÅŁte

-0.15

oops

-0.14

Yup

-0.14

POSITIVE LOGITS

 seriously

0.35

 come

0.28

 Wake

0.25

 Seriously

0.25

 surely

0.24

Seriously

0.24

 Come

0.24

 serious

0.23

ser

0.23

 wake

0.23

Activations Density 0.264%

expressions of frustration or disbelief

No Comments

No Known Activations