INDEX

Explanations

the word "of" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 irgend

-0.17

 quelque

-0.16

.codes

-0.16

-drop

-0.15

nonnull

-0.15

 Something

-0.14

opup

-0.14

æŁĲ

-0.14

 ÎºÎ¬

-0.14

lez

-0.14

POSITIVE LOGITS

 stuff

0.20

may

0.18

ones

0.16

hte

0.15

dm

0.15

it

0.15

/all

0.15

stuff

0.15

 overlap

0.15

imes

0.15

Activations Density 0.033%

the word "of" in various contexts

No Comments

No Known Activations