INDEX

Explanations

terms related to defense mechanisms or assertions of defense

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Palest

-0.16

nez

-0.16

Ð±Ð°Ð²

-0.16

reo

-0.15

imeline

-0.15

asic

-0.14

orz

-0.14

keit

-0.14

encil

-0.14

iga

-0.14

POSITIVE LOGITS

 against

0.21

 Against

0.20

nÃŃ

0.18

against

0.17

ably

0.17

Against

0.16

iston

0.16

0.15

ÛĮÙĩ

0.15

 proti

0.14

Activations Density 0.039%

terms related to defense mechanisms or assertions of defense

No Comments

No Known Activations