INDEX

Explanations

phrases indicating comparisons or evaluations of things or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 itself

-0.28

was

-0.21

å®ĥ

-0.20

çļĦä¸Ģä¸ª

-0.19

was

-0.18

its

-0.17

Its

-0.16

 wasn

-0.15

Its

-0.15

 Ð¾Ð½Ð¾

-0.15

POSITIVE LOGITS

 themselves

0.45

 ones

0.38

 examples

0.32

 those

0.31

nt

0.30

are

0.30

 exceptions

0.29

 originals

0.28

 reminders

0.28

 favorites

0.28

Activations Density 0.487%

phrases indicating comparisons or evaluations of things or ideas

No Comments

No Known Activations