INDEX

Explanations

aspects related to political figures and their actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Ã¶rt

-0.15

ersh

-0.15

ammo

-0.15

ÑĨÐµÐ¿

-0.14

pcm

-0.14

ataire

-0.14

bor

-0.14

.updateDynamic

-0.13

ahun

-0.13

jk

-0.13

POSITIVE LOGITS

 former

0.62

 Former

0.55

Former

0.49

former

0.49

 retired

0.37

 bÃ½val

0.34

 erst

0.32

 formerly

0.29

ex

0.29

 ÐºÐ¾Ð»Ð¸

0.27

Activations Density 0.162%

aspects related to political figures and their actions or statements

No Comments

No Known Activations