INDEX

Explanations

terms related to labor disputes and negotiations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Cust

-0.19

 cust

-0.19

cust

-0.18

 charged

-0.14

 credential

-0.14

 boon

-0.14

 Hancock

-0.14

itures

-0.14

atk

-0.14

-0.13

POSITIVE LOGITS

 redundancy

0.25

 dismiss

0.25

 redund

0.23

dismiss

0.23

TU

0.22

TU

0.21

 dismissal

0.21

acas

0.21

 sickness

0.20

 dismissed

0.19

Activations Density 0.053%

terms related to labor disputes and negotiations

No Comments

No Known Activations