INDEX

Explanations

words related to food and beverages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

inÃ§

-0.16

roat

-0.16

usc

-0.15

vor

-0.15

istant

-0.15

FormControl

-0.15

harma

-0.15

ainen

-0.14

ģ

-0.14

achable

-0.14

POSITIVE LOGITS

Sch

0.19

hammer

0.17

astic

0.15

ekim

0.15

ENAME

0.15

.AddWithValue

0.15

ãĤ¹ãĤ¯

0.14

ãĤ¹ãĤ³

0.14

kop

0.14

artz

0.14

Activations Density 0.025%

words related to food and beverages

No Comments

No Known Activations