INDEX

Explanations

information related to political actions and controversies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 tonight

-0.31

 tomorrow

-0.31

 Ð·Ð°Ð²ÑĤÑĢÐ°

-0.28

 recent

-0.26

 lately

-0.26

 Yesterday

-0.25

 newest

-0.25

 Recent

-0.25

 yesterday

-0.24

 Recently

-0.23

POSITIVE LOGITS

 then

0.39

then

0.30

 ÑĤÐ¾Ð³Ð´Ð°

0.29

Then

0.28

 Then

0.28

 famously

0.27

 THEN

0.26

 ëĭ¹ìĭľ

0.25

 entonces

0.23

 entÃ£o

0.23

Activations Density 0.347%

information related to political actions and controversies

No Comments

No Known Activations