INDEX

Explanations

references to military technology and nuclear weapons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 kindly

-0.17

kra

-0.15

istine

-0.14

lore

-0.14

Lug

-0.14

_boxes

-0.14

ä¾Ľ

-0.14

 Mason

-0.14

 alien

-0.13

amon

-0.13

POSITIVE LOGITS

æ´²

0.21

 ÑĪÐ°Ñħ

0.18

ovit

0.17

 strategic

0.16

-cap

0.16

 deterrent

0.16

 delivery

0.16

okoj

0.16

 Strategic

0.15

 Pose

0.15

Activations Density 0.027%

references to military technology and nuclear weapons

No Comments

No Known Activations