INDEX

Explanations

references to intrusion and security-related scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

aval

-0.18

ela

-0.15

avel

-0.15

ieux

-0.14

addle

-0.14

heim

-0.14

infer

-0.14

Ã¨m

-0.13

etal

-0.13

immel

-0.13

POSITIVE LOGITS

 entry

0.58

-entry

0.49

 Entry

0.49

 enter

0.47

 entering

0.47

 entrance

0.47

 enters

0.47

entry

0.47

è¿Ľåħ¥

0.46

åħ¥

0.45

Activations Density 0.198%

references to intrusion and security-related scenarios

No Comments

No Known Activations