INDEX

Explanations

names of notable individuals from various professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

elpers

-0.16

Æ°á»£t

-0.15

abic

-0.15

ollo

-0.14

 relic

-0.14

elps

-0.14

wd

-0.14

preserve

-0.14

occo

-0.13

 Williamson

-0.13

POSITIVE LOGITS

tee

0.14

TLC

0.13

ITTE

0.13

kyt

0.13

.CreateIndex

0.13

 butterfly

0.13

 å¤

0.13

ombat

0.13

Ø²Ø§ÙĨ

0.13

thest

0.12

Activations Density 0.011%

names of notable individuals from various professions

No Comments

No Known Activations

names of notable individuals from various professions

No Comments

No Known Activations