INDEX

Explanations

phrases indicating economic decline or decrease

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

up

-0.19

igon

-0.16

overe

-0.15

kou

-0.15

IAL

-0.15

quette

-0.15

aurant

-0.15

decode

-0.14

usto

-0.14

urette

-0.14

POSITIVE LOGITS

/down

0.31

graded

0.27

river

0.27

wards

0.26

/up

0.25

-down

0.24

grades

0.24

grading

0.22

played

0.22

ward

0.21

Activations Density 0.061%

phrases indicating economic decline or decrease

No Comments

No Known Activations