INDEX

Explanations

occurrences of the word "In."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

sofar

-0.16

Å¡ti

-0.15

Äįet

-0.15

locator

-0.15

AspectRatio

-0.14

.ribbon

-0.14

front

-0.14

ãĥ¬ãĥ¼

-0.14

 VOID

-0.14

jure

-0.14

POSITIVE LOGITS

 addition

0.26

 additional

0.22

 order

0.21

 additions

0.20

add

0.20

 Addition

0.20

 particular

0.18

 Fiscal

0.18

 house

0.17

add

0.17

Activations Density 0.095%

occurrences of the word "In."

No Comments

No Known Activations