INDEX

Explanations

references to notable historical figures and their contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

anding

-0.15

 Äĳi

-0.14

plode

-0.14

ialized

-0.14

nds

-0.14

etrain

-0.14

icode

-0.14

eted

-0.13

.Selenium

-0.13

odv

-0.13

POSITIVE LOGITS

elsius

0.18

peare

0.17

ius

0.16

openh

0.16

ï¸

0.16

hrd

0.15

 Masc

0.15

akespeare

0.15

éĨ

0.15

inus

0.14

Activations Density 0.297%

references to notable historical figures and their contributions

No Comments

No Known Activations