INDEX

Explanations

elements and features related to technology and equipment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ãĤ´ãĥª

-0.13

å®¹æĺĵ

-0.13

 takson

-0.12

ãĥĥãĥģ

-0.12

Î¬Î½ÏĦÎ±

-0.12

ugins

-0.12

ÙİØŃ

-0.12

ãĥ³ãĥ

-0.12

ÙĪØ§Ø¹

-0.12

ÑĢÑĥÑĤ

-0.12

POSITIVE LOGITS

 installed

0.38

 mounted

0.38

 hooked

0.34

 attached

0.34

 placed

0.31

installed

0.29

mounted

0.29

 fitted

0.28

 positioned

0.28

attached

0.28

Activations Density 0.264%

elements and features related to technology and equipment

No Comments

No Known Activations