INDEX

Explanations

references to the brain and its functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

tti

-0.17

tÃ¼r

-0.15

llum

-0.15

uldu

-0.14

gue

-0.14

oley

-0.14

uator

-0.14

getElement

-0.14

ams

-0.14

endet

-0.14

POSITIVE LOGITS

stem

0.34

iac

0.32

washing

0.29

waves

0.28

storms

0.28

storm

0.28

child

0.27

power

0.27

wave

0.27

Fog

0.23

Activations Density 0.014%

references to the brain and its functions

No Comments

No Known Activations