INDEX

Explanations

CSS properties and layout-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

agli

-0.18

]={↵

-0.15

illion

-0.14

irie

-0.14

arena

-0.14

rikes

-0.14

braco

-0.14

nop

-0.13

eler

-0.13

 Complex

-0.13

POSITIVE LOGITS

poke

0.15

alfa

0.15

 Favor

0.14

sson

0.14

 Citizenship

0.14

beam

0.14

oward

0.14

 Chall

0.14

aded

0.13

Activations Density 0.004%

CSS properties and layout-related terminology

No Comments

No Known Activations