INDEX

Explanations

references to geopolitical entities and diplomatic discussions, particularly involving North Korea

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

poÄįet

-0.14

.nano

-0.14

_IMPLEMENT

-0.14

 Walmart

-0.14

rev

-0.13

 æ¹

-0.13

 spraw

-0.13

laz

-0.13

esion

-0.13

Fle

-0.13

POSITIVE LOGITS

thon

0.16

_PWR

0.14

è¨Ģ

0.14

oker

0.14

ÐµÐ»ÑĮÐ½Ð¾

0.13

WL

0.13

ophil

0.13

pared

0.13

chg

0.13

 GREEN

0.13

Activations Density 0.009%

references to geopolitical entities and diplomatic discussions, particularly involving North Korea

No Comments

No Known Activations