INDEX

Explanations

mentions of governmental bodies or legislative institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 housing

-0.17

housing

-0.16

éĽĦ

-0.16

isma

-0.14

 housed

-0.14

arias

-0.14

nest

-0.14

inke

-0.14

ged

-0.13

agt

-0.13

POSITIVE LOGITS

 Representatives

0.36

 Commons

0.28

Represent

0.25

 commons

0.25

 Representative

0.25

 representatives

0.23

 cards

0.22

commons

0.21

 REPRESENT

0.21

 Represent

0.21

Activations Density 0.008%

mentions of governmental bodies or legislative institutions

No Comments

No Known Activations