INDEX

Explanations

disclaimers and statements regarding political neutrality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ean

-0.14

ipt

-0.14

ores

-0.13

ilog

-0.13

ï¼Ł↵↵

-0.13

Ã¨o

-0.13

igo

-0.13

cept

-0.13

isans

-0.13

angen

-0.13

POSITIVE LOGITS

 feel

0.41

Feel

0.41

 Feel

0.41

feel

0.37

 Enjoy

0.32

 enjoy

0.31

Enjoy

0.31

 hope

0.30

 please

0.29

Please

0.28

Activations Density 0.295%

disclaimers and statements regarding political neutrality

No Comments

No Known Activations