INDEX

Explanations

phrases that indicate the capability or permission to perform actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

uf

-0.14

ige

-0.14

 pomoc

-0.14

erdale

-0.13

ione

-0.13

å¸®

-0.13

RIPT

-0.13

idence

-0.13

essler

-0.13

.FAIL

-0.13

POSITIVE LOGITS

us

0.35

 them

0.22

him

0.21

you

0.20

 greater

0.18

for

0.17

raÅ¾

0.16

us

0.16

 flexibility

0.15

Activations Density 0.065%

phrases that indicate the capability or permission to perform actions

No Comments

No Known Activations