INDEX

Explanations

references to political debates and their related details

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

onom

-0.15

MLS

-0.14

uji

-0.14

ICA

-0.14

ruba

-0.14

PLL

-0.14

 subj

-0.13

ÃŃt

-0.13

alom

-0.13

POSITIVE LOGITS

 debate

0.52

 Debate

0.48

 debates

0.47

deb

0.43

Deb

0.38

 debating

0.37

 debated

0.35

deb

0.33

.deb

0.29

 moderators

0.23

Activations Density 0.059%

references to political debates and their related details

No Comments

No Known Activations