INDEX

Explanations

military ranks and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

emey

-0.16

pter

-0.16

ASSERT

-0.15

uco

-0.15

anker

-0.14

esti

-0.14

Integral

-0.14

èģ²

-0.14

 Judicial

-0.14

inic

-0.14

POSITIVE LOGITS

 Stuff

0.16

Cle

0.15

asctime

0.15

 colored

0.15

Ä±s

0.14

å¦

0.14

áºŃn

0.14

onia

0.14

Raf

0.14

 Sick

0.14

Activations Density 0.020%

military ranks and titles

No Comments

No Known Activations