INDEX

Explanations

phrases indicating subjectivity or personal perception

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

him

-0.16

 themselves

-0.15

them

-0.15

ÙĴÙĩ

-0.14

icare

-0.14

 himself

-0.14

eux

-0.14

ighbors

-0.14

ught

-0.13

agues

-0.13

POSITIVE LOGITS

 there

0.29

 clear

0.26

 apparent

0.24

 like

0.24

we

0.23

 likely

0.23

 they

0.21

 evident

0.21

 counter

0.20

 that

0.19

Activations Density 0.030%

phrases indicating subjectivity or personal perception

No Comments

No Known Activations