INDEX

Explanations

phrases related to data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ade

-0.16

idity

-0.15

 Suff

-0.15

 Avenue

-0.14

Hor

-0.14

 Wilde

-0.14

POSITIVE LOGITS

ìłĢ

0.16

YYS

0.15

Ø³ÙĦ

0.14

 Suns

0.14

robat

0.14

mtree

0.14

>true

0.13

èĥİ

0.13

ĥĿ

0.13

atted

0.13

Activations Density 0.009%

phrases related to data and statistics

No Comments

No Known Activations