INDEX

Explanations

phrases related to significant political decisions and actions within governmental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

','=',$

-0.18

abella

-0.16

qli

-0.16

reesome

-0.16

abelle

-0.15

Ã©ny

-0.14

 cole

-0.14

Yi

-0.14

ares

-0.14

Meg

-0.14

POSITIVE LOGITS

0.16

eks

0.16

inic

0.15

rung

0.15

 manuals

0.15

oggler

0.14

 sert

0.14

atsby

0.14

 incor

0.14

elor

0.14

Activations Density 0.216%

phrases related to significant political decisions and actions within governmental contexts

No Comments

No Known Activations