INDEX

Explanations

references to financial status and personal background information about individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uario

-0.15

aptor

-0.15

Os

-0.14

itech

-0.14

Å¼e

-0.14

ossier

-0.14

itori

-0.14

qv

-0.14

stick

-0.13

 Hunts

-0.13

POSITIVE LOGITS

tica

0.18

eric

0.15

ikal

0.15

iare

0.15

.Exists

0.15

arat

0.14

Ø±Ùĥ

0.14

ropolis

0.14

ADVERTISEMENT

0.14

rott

0.14

Activations Density 0.002%

references to financial status and personal background information about individuals

No Comments

No Known Activations