INDEX

Explanations

references to financial results and operational performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÙĬÙĩ

-0.15

Voj

-0.15

ka

-0.14

pdb

-0.14

ua

-0.13

its

-0.13

lix

-0.13

 Prince

-0.13

POSITIVE LOGITS

 below

0.28

 above

0.25

 Ð½Ð¸Ð¶Ðµ

0.23

below

0.20

 Ð²ÑĭÑĪÐµ

0.20

 yukarÄ±

0.18

_below

0.18

above

0.18

 Below

0.17

 BELOW

0.17

Activations Density 0.220%

references to financial results and operational performance

No Comments

No Known Activations