INDEX

Explanations

occurrences of various forms of the word "as."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.22

tm

-0.21

kal

-0.20

yar

-0.20

han

-0.19

ÛĮ

-0.19

eing

-0.19

kÃ¡

-0.19

hum

-0.19

hu

-0.18

POSITIVE LOGITS

aurus

0.19

phalt

0.18

sembler

0.17

ãĤ±ãĥĥãĥĪ

0.17

nost

0.17

íĭ±

0.17

hton

0.16

ional

0.16

fak

0.16

gow

0.16

Activations Density 0.102%

occurrences of various forms of the word "as."

No Comments

No Known Activations