INDEX

Explanations

references to security threats and violent events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.Atomic

-0.17

 retVal

-0.14

roman

-0.14

inati

-0.14

AZY

-0.14

igin

-0.13

collapse

-0.13

uguay

-0.13

heiro

-0.13

POSITIVE LOGITS

 Frontier

0.18

Disappear

0.17

 Cameroon

0.16

operand

0.15

Idle

0.15

aye

0.15

 Nigeria

0.14

ossa

0.14

 villages

0.14

 Nigerian

0.14

Activations Density 0.024%

references to security threats and violent events

No Comments

No Known Activations