INDEX

Explanations

specific legal or regulatory terminologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

.Aggressive

-0.17

delegate

-0.16

_De

-0.15

 Gilles

-0.15

 delegate

-0.14

 sqlCommand

-0.14

 HRESULT

-0.14

 Fleet

-0.14

inton

-0.14

atr

-0.14

POSITIVE LOGITS

es

0.21

ES

0.21

Ã¨s

0.20

ES

0.19

ÐµÑģ

0.18

 Essex

0.17

 Norm

0.17

-es

0.17

 pressure

0.17

esh

0.16

Activations Density 0.023%

specific legal or regulatory terminologies

No Comments

No Known Activations