INDEX

Explanations

specific terms related to immune system function and cellular processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

æĭħå½ĵ

-0.14

_embed

-0.14

lech

-0.14

ropolis

-0.14

ãĤº

-0.14

eless

-0.14

Ø±ÛĮØ¨

-0.14

istol

-0.13

oneksi

-0.13

erokee

-0.13

POSITIVE LOGITS

CD

0.33

/memory

0.29

Th

0.29

 memory

0.29

eff

0.27

CD

0.26

 Memory

0.25

-memory

0.24

 helper

0.23

Memory

0.23

Activations Density 0.023%

specific terms related to immune system function and cellular processes

No Comments

No Known Activations