INDEX

Explanations

phrases related to emotional impact and negative consequences of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-Mart

-0.16

åŁ

-0.15

zion

-0.15

Ð¾ÑĢÐ°Ð·

-0.14

íĭ±

-0.14

ibo

-0.14

.lt

-0.14

indsight

-0.14

zew

-0.14

.crt

-0.14

POSITIVE LOGITS

 onto

0.40

onto

0.36

 into

0.29

into

0.24

 INTO

0.21

Ont

0.20

 Into

0.19

 unto

0.19

 upon

0.19

_into

0.19

Activations Density 0.267%

phrases related to emotional impact and negative consequences of actions

No Comments

No Known Activations