INDEX

Explanations

phrases indicating physical actions or movements associated with people and their interactions

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

 ########.

-0.19

å²¡

-0.14

acman

-0.14

 ç¿

-0.13

åĦ

-0.13

edd

-0.13

:\/\/

-0.13

Ø¹Ø§

-0.13

 Fortune

-0.13

POSITIVE LOGITS

yal

0.15

 Sharma

0.15

agne

0.14

ENTE

0.14

rial

0.14

awi

0.14

quire

0.14

icap

0.14

HexString

0.14

(Resource

0.13

Activations Density 0.716%

phrases indicating physical actions or movements associated with people and their interactions

No Comments

No Known Activations