INDEX

Explanations

terms related to trade secrets and confidentiality agreements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ĵĺ

-0.16

aku

-0.16

abay

-0.16

onde

-0.15

ande

-0.15

owl

-0.15

nell

-0.15

è¸

-0.14

amedi

-0.14

deaux

-0.14

POSITIVE LOGITS

Dam

0.17

 spread

0.17

ossip

0.16

 Busy

0.15

ret

0.15

eph

0.14

osy

0.14

 trim

0.14

langs

0.14

 Dram

0.14

Activations Density 0.019%

terms related to trade secrets and confidentiality agreements

No Comments

No Known Activations