INDEX

Explanations

titles and ranks related to military personnel

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÎĨ

-0.14

dio

-0.14

 kako

-0.14

rof

-0.13

.gameserver

-0.13

 seni

-0.13

ulario

-0.13

::*

-0.13

_interfaces

-0.13

.openConnection

-0.13

POSITIVE LOGITS

Ð»ÐµÐ¹

0.17

-major

0.17

ieved

0.17

lech

0.16

owie

0.15

eneral

0.15

nic

0.15

amic

0.15

0.14

Activations Density 0.031%

titles and ranks related to military personnel

No Comments

No Known Activations