INDEX

Explanations

terms related to employment, disability, and financial hardship

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

åī²

-0.15

erten

-0.15

indow

-0.14

 Ø¯Ùģ

-0.14

ISMATCH

-0.14

ANGER

-0.13

resh

-0.13

 unintended

-0.13

     č↵

-0.13

 privileges

-0.13

POSITIVE LOGITS

 illness

0.22

 natural

0.21

 circumstances

0.20

 extreme

0.19

 reasons

0.19

 force

0.19

 acts

0.19

azzi

0.19

 weather

0.19

 Force

0.19

Activations Density 0.164%

terms related to employment, disability, and financial hardship

No Comments

No Known Activations