INDEX

Explanations

descriptions of explosive events and their aftermath

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.16

mlin

-0.16

éĢł

-0.16

ayet

-0.15

 kraje

-0.15

 bombed

-0.14

Ð³Ð¾ÑĤ

-0.14

umpy

-0.14

 handjob

-0.14

 Attacks

-0.14

POSITIVE LOGITS

 Conc

0.21

 cause

0.20

 knock

0.20

 Knock

0.19

 dent

0.18

 panc

0.18

 vapor

0.18

gou

0.18

 critically

0.17

 conc

0.17

Activations Density 0.134%

descriptions of explosive events and their aftermath

No Comments

No Known Activations