INDEX

Explanations

occurrences of voting and legislative actions

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

 Consort

-0.15

ÑĥÑİÑīÐ¸Ð¹

-0.14

ump

-0.14

 (*((

-0.14

ÅĻÃŃ

-0.14

umper

-0.14

chy

-0.14

 ÄĳÃłi

-0.13

 legislative

-0.13

addon

-0.13

POSITIVE LOGITS

 vote

0.25

 unanimously

0.24

 votes

0.24

 overwhelming

0.23

 unanimous

0.23

 overwhelmingly

0.21

 Ð³Ð¾Ð»Ð¾Ñģ

0.21

 unanim

0.19

vote

0.19

 voted

0.19

Activations Density 0.073%

occurrences of voting and legislative actions

No Comments

No Known Activations