INDEX

Explanations

complex and multi-syllabic words in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

echn

-0.17

imes

-0.15

ullan

-0.15

incinn

-0.14

alic

-0.14

ibus

-0.14

odata

-0.14

utenberg

-0.14

 Albany

-0.14

DAQ

-0.13

POSITIVE LOGITS

0.15

sthrough

0.14

enco

0.14

dete

0.14

pageIndex

0.14

Lif

0.14

çħ

0.14

 Whole

0.13

à¹īà¸ĩ

0.13

Activations Density 0.111%

complex and multi-syllabic words in various contexts

No Comments

No Known Activations