INDEX

Explanations

terms related to survival and security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

çĿ

-0.15

RIPT

-0.15

ensem

-0.14

ipa

-0.14

ildren

-0.14

 Jacqu

-0.14

 {?>↵

-0.14

ÛĮØ±Ùĩ

-0.14

aneous

-0.14

isay

-0.14

POSITIVE LOGITS

Mos

0.18

Tir

0.16

 mater

0.15

 stuff

0.14

 Thur

0.14

å¹²

0.14

Lets

0.14

qui

0.14

\:

0.14

elters

0.13

Activations Density 0.000%

terms related to survival and security

No Comments

No Known Activations