INDEX

Explanations

terms related to "monks" or "monasteries."

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

leton

-0.19

istrovstvÃŃ

-0.17

zig

-0.15

ëıĮ

-0.15

ONS

-0.15

Ø§Ø¹Ø¯

-0.15

ibase

-0.15

mund

-0.14

 Calendar

-0.14

 combin

-0.14

POSITIVE LOGITS

astery

0.15

hill

0.15

zo

0.15

poz

0.14

æ¶

0.14

hdl

0.14

ParameterValue

0.14

.Framework

0.14

ezi

0.13

upp

0.13

Activations Density 0.018%

terms related to "monks" or "monasteries."

No Comments

No Known Activations