INDEX

Explanations

references to notable events or incidents involving specific individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

quette

-0.16

Ð¾Ð±Ð¾Ð²

-0.14

UpInside

-0.14

krom

-0.14

ofilm

-0.14

 hookup

-0.14

Partition

-0.14

.partition

-0.14

 partitions

-0.13

enor

-0.13

POSITIVE LOGITS

 Scal

0.30

 shooter

0.30

 gunman

0.30

 shooting

0.27

 Hodg

0.26

 Shooter

0.26

Gab

0.25

 shootings

0.25

 rifle

0.23

 Shooting

0.22

Activations Density 0.005%

references to notable events or incidents involving specific individuals

No Comments

No Known Activations