INDEX

Explanations

references to legal issues and disputes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

iqueta

-0.18

uzzi

-0.18

anon

-0.17

 Sanity

-0.16

anzi

-0.16

zept

-0.14

pter

-0.14

kos

-0.14

 innoc

-0.14

 chod

-0.14

POSITIVE LOGITS

did

0.20

 obst

0.19

0.18

 habit

0.17

 obstruct

0.17

 responsible

0.17

 using

0.17

hyp

0.16

not

0.16

 Habit

0.16

Activations Density 0.256%

references to legal issues and disputes

No Comments

No Known Activations