INDEX

Explanations

references to legislative hearings and governmental committees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lassian

-0.17

ournal

-0.16

Ø¬ÙĬ

-0.15

elda

-0.15

JOR

-0.15

.appspot

-0.14

ungan

-0.14

 envelopes

-0.14

iag

-0.14

ucci

-0.14

POSITIVE LOGITS

 hearing

0.38

 hearings

0.33

 committee

0.33

 Hearing

0.32

 Committee

0.32

 witnesses

0.30

hear

0.28

 testimony

0.27

 Witnesses

0.27

 markup

0.27

Activations Density 0.067%

references to legislative hearings and governmental committees

No Comments

No Known Activations