INDEX

Explanations

concepts related to consequences and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

aeper

-0.16

apesh

-0.15

itsu

-0.15

requencies

-0.15

ertz

-0.15

oku

-0.15

 Abuse

-0.15

ÃŃnh

-0.14

eson

-0.14

Slash

-0.14

POSITIVE LOGITS

 when

0.26

when

0.23

khi

0.23

When

0.20

 upon

0.19

_when

0.18

 cuando

0.18

 When

0.18

 quando

0.18

 after

0.17

Activations Density 0.486%

concepts related to consequences and their implications

No Comments

No Known Activations