INDEX

Explanations

historical references related to architecture and significant buildings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

chester

-0.16

 Nath

-0.14

.zoom

-0.14

 lava

-0.14

 Assistance

-0.14

anova

-0.14

amen

-0.14

 stol

-0.13

á»ĳt

-0.13

ĵį

-0.13

POSITIVE LOGITS

0.34

0.33

0.31

0.29

0.27

0.24

 Renaissance

0.24

Tud

0.21

Activations Density 0.049%

historical references related to architecture and significant buildings

No Comments

No Known Activations