INDEX

Explanations

words and phrases related to reporting or documentation of events or incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ehler

-0.15

iring

-0.15

iglia

-0.15

combe

-0.14

ÑĢÐ°Ð

-0.14

 factor

-0.14

acre

-0.14

 Gros

-0.14

/simple

-0.14

à¸²à¸£

-0.14

POSITIVE LOGITS

edly

0.20

atest

0.16

agens

0.15

VICES

0.15

sdale

0.14

ç«ł

0.14

tn

0.14

 sÃ³ng

0.14

hung

0.14

ossa

0.14

Activations Density 0.049%

words and phrases related to reporting or documentation of events or incidents

No Comments

No Known Activations