INDEX

Explanations

references to kits or kit-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

æ³ģ

-0.18

edException

-0.17

oins

-0.17

edula

-0.17

edes

-0.16

ADS

-0.16

egers

-0.16

erb

-0.16

ois

-0.15

hound

-0.15

POSITIVE LOGITS

ting

0.22

tridge

0.19

tem

0.19

estring

0.19

Kat

0.18

kat

0.18

itial

0.18

tle

0.17

kat

0.17

tee

0.17

Activations Density 0.014%

references to kits or kit-related terminology

No Comments

No Known Activations