INDEX

Explanations

food and beverage-related terms, particularly those highlighting flavors and qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ux

-0.16

orf

-0.15

ëª

-0.15

isson

-0.14

Py

-0.14

aget

-0.14

lur

-0.14

 Kavanaugh

-0.14

cli

-0.13

isko

-0.13

POSITIVE LOGITS

adla

0.15

eyin

0.15

Ø²Ø±

0.15

urum

0.14

/loader

0.14

odÃŃ

0.14

-prepend

0.14

 uten

0.14

antha

0.14

zers

0.14

Activations Density 0.338%

food and beverage-related terms, particularly those highlighting flavors and qualities

No Comments

No Known Activations