INDEX

Explanations

concepts related to system changes and upgrades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Î³Ïĩ

-0.14

igid

-0.14

azo

-0.12

chw

-0.12

FromArray

-0.12

TOT

-0.11

ä¸Ķ

-0.11

 ÙĦÙĩØ§

-0.11

entine

-0.11

utan

-0.11

POSITIVE LOGITS

 ÑĩÑĤÐ¾Ð±Ñĭ

0.75

 Äĳá»ĥ

0.68

to

0.65

 afin

0.63

 inorder

0.61

 ÑīÐ¾Ð±

0.59

 nháº±m

0.48

aby

0.45

ä¸ºäºĨ

0.44

 Ð§ÑĤÐ¾Ð±Ñĭ

0.40

Activations Density 2.580%

concepts related to system changes and upgrades

No Comments

No Known Activations