INDEX

Explanations

file path indicators and references to programming or scripting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

eum

-0.18

ecz

-0.16

egree

-0.16

zig

-0.16

lical

-0.15

typeid

-0.15

tesy

-0.15

zes

-0.14

Ħĸ

-0.14

tical

-0.14

POSITIVE LOGITS

adows

0.37

adow

0.37

ield

0.34

akespeare

0.34

ields

0.34

elter

0.32

ooting

0.32

utdown

0.31

uffle

0.30

apiro

0.30

Activations Density 0.031%

file path indicators and references to programming or scripting elements

No Comments

No Known Activations