INDEX

Explanations

special characters or symbols within the text, indicating formatting or emphasis rather than actual words

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

çºª

-0.15

Î¯Î¿Ïħ

-0.15

ÅĽnie

-0.15

adox

-0.14

éĳ

-0.14

/init

-0.14

erk

-0.14

éļĨ

-0.14

iferay

-0.14

Ð»Ð¸Ñĩ

-0.14

POSITIVE LOGITS

us

0.15

à¸²à¸¢

0.14

 else

0.14

Ã¤nd

0.14

reme

0.14

arer

0.14

 cust

0.14

 intervening

0.13

å¹

0.13

ets

0.13

Activations Density 0.017%

special characters or symbols within the text, indicating formatting or emphasis rather than actual words

No Comments

No Known Activations