INDEX

Explanations

references to dictionaries and vocabulary-related terms

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

 Dana

-0.17

ldr

-0.16

lops

-0.16

isha

-0.14

dots

-0.14

Doug

-0.14

ellas

-0.14

 duplex

-0.14

 ç¯

-0.14

ynn

-0.14

POSITIVE LOGITS

 dictionary

0.57

 directory

0.53

 Dictionary

0.48

 Directory

0.47

 directories

0.46

 dictionaries

0.46

dictionary

0.46

dic

0.43

Dictionary

0.43

directory

0.42

Activations Density 0.142%

references to dictionaries and vocabulary-related terms

No Comments

No Known Activations