INDEX

Explanations

phrases related to liability and warranty disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

activex

-0.16

steder

-0.16

ãĤ·ãĤ¢

-0.15

/fwlink

-0.15

baugh

-0.14

riad

-0.14

abeth

-0.14

ISOString

-0.14

AINS

-0.13

hausen

-0.13

POSITIVE LOGITS

ÏĦÏĥ

0.16

ike

0.16

LAG

0.15

ose

0.15

kas

0.14

 conditions

0.14

hel

0.14

 condition

0.14

kova

0.13

ed

0.13

Activations Density 0.001%

phrases related to liability and warranty disclaimers

No Comments

No Known Activations