INDEX

Explanations

phrases related to packaging and product quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

orns

-0.17

Ð¾ÑģÑĤ

-0.15

sl

-0.15

abase

-0.14

mods

-0.14

essler

-0.14

ekl

-0.13

 brass

-0.13

earer

-0.13

Cly

-0.13

POSITIVE LOGITS

 soften

0.15

McN

0.14

peria

0.14

ouser

0.13

riter

0.13

ellar

0.13

ongan

0.13

ymb

0.13

Activations Density 0.043%

phrases related to packaging and product quantities

No Comments

No Known Activations