INDEX

Explanations

phrases related to placing or causing burdens and pressures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

qt

-0.16

ubo

-0.14

 Hlav

-0.14

odos

-0.14

iÃŁ

-0.14

ledo

-0.14

 outr

-0.14

UIT

-0.13

ighet

-0.13

POSITIVE LOGITS

 pressure

0.40

 strain

0.35

 Pressure

0.32

pressure

0.31

 strains

0.28

-pressure

0.26

Pressure

0.26

 stress

0.25

_pressure

0.24

 pressures

0.24

Activations Density 0.032%

phrases related to placing or causing burdens and pressures

No Comments

No Known Activations