INDEX

Explanations

phrases indicating similarity or comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

doing

-0.19

Doing

-0.17

 doing

-0.17

 Doing

-0.16

 Undert

-0.15

seau

-0.15

 ÏĦÏģÏĮ

-0.15

 undert

-0.15

yro

-0.15

 undertaking

-0.15

POSITIVE LOGITS

 justice

0.30

job

0.25

 damage

0.25

 things

0.24

 jobs

0.24

 Damage

0.23

 thing

0.23

 tasks

0.23

justice

0.22

cket

0.22

Activations Density 0.183%

phrases indicating similarity or comparison

No Comments

No Known Activations

phrases indicating similarity or comparison

No Comments

No Known Activations