INDEX

Explanations

actions related to employment and workload

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 nineteenth

-0.14

 Eleven

-0.13

åįģåħ«

-0.12

uentes

-0.12

ulu

-0.12

 minul

-0.12

nown

-0.12

ITTE

-0.12

 à¤¸à¤¦

-0.12

ä»Ĭ

-0.12

POSITIVE LOGITS

 between

0.71

 anywhere

0.62

up

0.60

between

0.54

 Between

0.50

 upto

0.50

 around

0.49

 about

0.48

Between

0.47

-between

0.46

Activations Density 0.429%

actions related to employment and workload

No Comments

No Known Activations