INDEX

Explanations

repeated phrases or concepts that indicate similarity

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

related

-0.16

 itself

-0.15

#ac

-0.15

loff

-0.14

the

-0.14

rac

-0.14

requ

-0.13

 better

-0.13

any

-0.13

rious

-0.13

POSITIVE LOGITS

 exact

0.43

 thing

0.42

-sex

0.41

 kind

0.38

 kinds

0.35

 sort

0.35

 amount

0.33

 type

0.33

exact

0.32

-old

0.31

Activations Density 0.083%

repeated phrases or concepts that indicate similarity

No Comments

No Known Activations