INDEX

Explanations

years and numerical data in a range

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÑıÐ¼

-0.15

ÃľRK

-0.15

iesel

-0.15

unj

-0.14

Ð½Ð¾Ð¿

-0.14

 reim

-0.13

uve

-0.13

.mybatisplus

-0.13

oca

-0.13

uir

-0.13

POSITIVE LOGITS

olini

0.17

0.15

0.14

eteria

0.14

venge

0.14

ington

0.13

INGTON

0.13

nor

0.13

Activations Density 0.115%

years and numerical data in a range

No Comments

No Known Activations