INDEX

Explanations

individual names and notable figures, particularly those associated with media and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ãĥ¼ãĥł

-0.16

 challenge

-0.15

ose

-0.15

 Polar

-0.14

 Transition

-0.14

eder

-0.14

âĢĮØ³ÛĮ

-0.14

ignum

-0.13

çĤİ

-0.13

 opak

-0.13

POSITIVE LOGITS

 paul

0.22

 Paul

0.18

criptor

0.16

nodoc

0.15

zzo

0.15

 isten

0.15

odor

0.15

 '\''

0.15

adlo

0.15

Paul

0.14

Activations Density 0.027%

individual names and notable figures, particularly those associated with media and entertainment

No Comments

No Known Activations