INDEX

Explanations

words that convey evaluations or judgments about people or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

oe

-0.16

-0.15

ayo

-0.14

urtle

-0.14

awan

-0.14

rij

-0.14

 hoping

-0.13

Gig

-0.13

xab

-0.13

odied

-0.13

POSITIVE LOGITS

 result

0.29

due

0.29

due

0.28

 based

0.26

 resultado

0.25

_due

0.24

 thanks

0.23

 resultat

0.23

 driven

0.23

thanks

0.23

Activations Density 0.012%

words that convey evaluations or judgments about people or situations

No Comments

No Known Activations