INDEX

Explanations

phrases related to loading processes or functions

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

loating

-0.16

Ð½Ð°ÑĢÐ¾Ð´

-0.16

/how

-0.15

bread

-0.15

/all

-0.15

leri

-0.14

Ware

-0.14

lou

-0.14

adle

-0.14

iner

-0.14

POSITIVE LOGITS

edException

0.19

ings

0.18

iciel

0.18

edImage

0.17

nict

0.15

zÃŃ

0.15

ubre

0.15

Å¾iv

0.15

mates

0.14

mate

0.14

Activations Density 0.031%

phrases related to loading processes or functions

No Comments

No Known Activations