INDEX

Explanations

terms related to sealing and safety issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

secure

-0.18

 sÃ©cur

-0.18

ting

-0.17

rag

-0.17

ÑıÐ¶

-0.16

enez

-0.16

 secure

-0.16

åĢĳ

-0.15

-quarters

-0.15

secured

-0.15

POSITIVE LOGITS

éĴŁ

0.21

bastian

0.21

URITY

0.20

bast

0.20

LECTION

0.18

antically

0.17

conde

0.17

glass

0.17

urity

0.16

imits

0.16

Activations Density 0.069%

terms related to sealing and safety issues

No Comments

No Known Activations