INDEX

Explanations

phrases and concepts related to critique or moral judgment, particularly regarding hypocrisy and social issues

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

lingen

-0.15

rier

-0.15

ecko

-0.14

ãĥĥãĥģ

-0.14

 eiusmod

-0.14

/pg

-0.14

utch

-0.14

 THEN

-0.14

asty

-0.13

POSITIVE LOGITS

isas

0.15

 pale

0.14

nor

0.14

imoto

0.14

EMS

0.14

çĶŁ

0.13

jen

0.13

emez

0.13

.rpm

0.13

 Guill

0.13

Activations Density 0.121%

phrases and concepts related to critique or moral judgment, particularly regarding hypocrisy and social issues

No Comments

No Known Activations