INDEX

Explanations

mentions of cheating or related behaviors involving trust violations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

xin

-0.16

illes

-0.15

Attrib

-0.15

killer

-0.15

ASTE

-0.14

ãĥ¬ãĤ¹

-0.14

perimental

-0.14

out

-0.14

orsche

-0.14

igest

-0.14

POSITIVE LOGITS

vron

0.16

vrolet

0.16

yÅ¡

0.16

asley

0.15

Ģë¡ľ

0.15

BuilderInterface

0.14

urga

0.14

resume

0.14

Activations Density 0.035%

mentions of cheating or related behaviors involving trust violations

No Comments

No Known Activations