INDEX

Explanations

references to historical events and their implications

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

-0.25

-0.23

-0.20

tv

-0.20

_TV

-0.20

-0.19

 televised

-0.19

 televis

-0.19

 television

-0.19

POSITIVE LOGITS

0.60

0.48

WW

0.35

 Bolshevik

0.33

0.28

 Bols

0.26

Û±Û¹

0.21

 bols

0.21

 twenties

0.21

WW

0.20

Activations Density 0.293%

references to historical events and their implications

No Comments

No Known Activations