INDEX

Explanations

the word "from" 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

å¾ŀ

-0.16

FromFile

-0.16

á»«

-0.15

.Interop

-0.15

ãģĭãĤī

-0.15

unas

-0.15

unma

-0.15

FromClass

-0.14

Ð²ÑĸÐ´

-0.14

ÙĦÙĬÙĦ

-0.14

POSITIVE LOGITS

/to

0.40

/by

0.26

 scratch

0.24

/of

0.24

/about

0.23

scratch

0.21

the

0.20

 being

0.20

mers

0.20

 whence

0.20

Activations Density 0.308%

the word "from" in various contexts

No Comments

No Known Activations