INDEX

Explanations

references to threats and security concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ideographic

-0.18

 revis

-0.17

igation

-0.17

tlement

-0.17

geries

-0.16

oucÃŃ

-0.15

IGATION

-0.15

ÙĪÛĮÛĮ

-0.15

 salv

-0.15

ules

-0.14

POSITIVE LOGITS

ify

0.31

ize

0.30

ise

0.24

itize

0.24

inize

0.23

iliate

0.23

elize

0.22

inate

0.22

isify

0.21

minate

0.21

Activations Density 0.240%

references to threats and security concerns

No Comments

No Known Activations

references to threats and security concerns

No Comments

No Known Activations