INDEX

Explanations

references to security measures and military capabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

iston

-0.17

ÐºÐ°Ð¶

-0.16

_Bool

-0.15

Ð¾ÐºÑĢÐµÐ¼

-0.15

 Ð¿ÑĢÐ°Ð²Ð°

-0.15

 PropertyValue

-0.14

 Strand

-0.14

InterfaceOrientation

-0.14

 @"↵

-0.14

 Bomb

-0.13

POSITIVE LOGITS

 Chief

0.17

Chief

0.16

 task

0.15

 Social

0.15

resses

0.15

 troll

0.14

rip

0.14

 Commonwealth

0.14

ritel

0.14

rip

0.14

Activations Density 0.194%

references to security measures and military capabilities

No Comments

No Known Activations