INDEX

Explanations

references to awards and accolades

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

rai

-0.15

 Brah

-0.15

éĻµ

-0.15

 gross

-0.14

iti

-0.14

.OUT

-0.14

iller

-0.14

onda

-0.14

ild

-0.14

lect

-0.14

POSITIVE LOGITS

ipes

0.16

ROL

0.16

ing

0.15

anan

0.15

Ø´Øª

0.15

Ú¯Ø±ÛĮ

0.15

reds

0.14

ssp

0.14

#ga

0.14

nable

0.14

Activations Density 0.006%

references to awards and accolades

No Comments

No Known Activations