INDEX

Explanations

references to military and defense-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.Globalization

-0.18

.GeneratedValue

-0.17

fod

-0.15

gnu

-0.14

 Hezbollah

-0.14

 Highlander

-0.14

.getHeader

-0.14

 ê²Į

-0.14

.FormBorderStyle

-0.14

 Gandhi

-0.13

POSITIVE LOGITS

Âłm

0.15

 Uncategorized

0.14

 latter

0.13

 madness

0.13

Ã³ria

0.13

ÂłM

0.13

moo

0.13

inha

0.12

.SharedPreferences

0.12

laz

0.12

Activations Density 0.079%

references to military and defense-related topics

No Comments

No Known Activations