INDEX

Explanations

references to personal relationships and familial connections

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

HAS

-0.27

Were

-0.27

 Were

-0.26

Has

-0.26

—are

-0.25

_are

-0.24

.are

-0.23

 hanno

-0.23

_has

-0.23

 aren

-0.23

POSITIVE LOGITS

was

0.40

 wasn

0.30

 became

0.27

 could

0.25

 couldn

0.25

was

0.24

 took

0.23

 began

0.23

had

0.22

 would

0.22

Activations Density 0.512%

references to personal relationships and familial connections

No Comments

No Known Activations