INDEX

Explanations

occurrences of the name "Kent" and its variations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

arness

-0.17

aturas

-0.16

ators

-0.15

Ã¡ÅĻ

-0.15

geh

-0.15

amient

-0.14

bum

-0.14

se

-0.14

antine

-0.14

aments

-0.13

POSITIVE LOGITS

ucky

0.44

uck

0.30

UCK

0.28

mere

0.27

aro

0.24

uky

0.24

eken

0.23

ucker

0.20

gens

0.19

ucking

0.18

Activations Density 0.004%

occurrences of the name "Kent" and its variations within the text

No Comments

No Known Activations