INDEX

Explanations

terms related to military forces and land-based operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

etros

-0.16

 ÑģÐ¾Ð±Ð¾Ð¹

-0.16

ippy

-0.14

etty

-0.14

ÏĢÎ»

-0.14

APTER

-0.14

.FindGameObjectWithTag

-0.14

necessary

-0.14

lia

-0.14

 ÑģÐ¾Ð±Ð¾Ñİ

-0.14

POSITIVE LOGITS

aled

0.17

ãĤ¤ãĤ¯

0.15

isch

0.14

atter

0.14

iliz

0.13

unan

0.13

anne

0.13

ura

0.13

ardo

0.13

 acomp

0.13

Activations Density 0.091%

terms related to military forces and land-based operations

No Comments

No Known Activations