INDEX

Explanations

usages of the word 'to' and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 thá»ķ

-0.13

untas

-0.13

euillez

-0.12

undler

-0.12

aben

-0.12

.ReadAll

-0.12

_firestore

-0.12

 addObject

-0.12

errat

-0.12

cretion

-0.12

POSITIVE LOGITS

 look

1.30

 Look

1.17

look

1.16

 LOOK

1.11

Look

1.07

 looking

1.05

 looks

1.04

 looked

1.04

LOOK

0.99

_look

0.98

Activations Density 0.271%

usages of the word 'to' and its variations in context

No Comments

No Known Activations