INDEX

Explanations

proper nouns, particularly names and titles featuring 'ee' vowel combinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

st

-0.22

stem

-0.19

thal

-0.19

tt

-0.18

ynos

-0.17

ness

-0.17

tn

-0.17

td

-0.17

nya

-0.17

icken

-0.16

POSITIVE LOGITS

zers

0.24

uw

0.23

eee

0.22

bles

0.21

zy

0.20

pee

0.20

zer

0.20

ple

0.19

pest

0.18

hive

0.17

Activations Density 0.027%

proper nouns, particularly names and titles featuring 'ee' vowel combinations

No Comments

No Known Activations