INDEX

Explanations

references to medical and legal decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 amongst

-0.32

 whilst

-0.31

 Towards

-0.30

 towards

-0.30

owards

-0.28

 Whilst

-0.27

‘

-0.26

Towards

-0.25

 Firstly

-0.25

 judgement

-0.24

POSITIVE LOGITS

 nons

0.26

 nonzero

0.20

 Dumpster

0.20

 nonexistent

0.19

 prere

0.19

 autogenerated

0.18

uyla

0.16

 multis

0.16

 nond

0.16

sem

0.16

Activations Density 0.607%

references to medical and legal decision-making

No Comments

No Known Activations