INDEX

Explanations

phrases related to secrecy and privacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 bypass

-0.21

 past

-0.21

 passed

-0.20

Past

-0.20

 Past

-0.19

 Passed

-0.19

past

-0.19

 pass

-0.17

 passes

-0.17

_past

-0.16

POSITIVE LOGITS

ahr

0.16

iten

0.15

 secret

0.15

tainment

0.15

ç§ĺ

0.15

èĳ

0.15

issen

0.15

 receipt

0.15

 selfish

0.15

.localized

0.15

Activations Density 0.042%

phrases related to secrecy and privacy

No Comments

No Known Activations