INDEX

Explanations

references to notable individuals associated with terrorist organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

celik

-0.17

abant

-0.15

å·¡

-0.15

èĢ

-0.15

 eskort

-0.14

aben

-0.14

agna

-0.14

fen

-0.14

rouw

-0.14

cmc

-0.14

POSITIVE LOGITS

 operational

0.16

oord

0.15

finalize

0.15

ISI

0.15

 oper

0.14

 operations

0.14

alink

0.14

 Plot

0.14

 master

0.14

 Sender

0.14

Activations Density 0.040%

references to notable individuals associated with terrorist organizations

No Comments

No Known Activations