INDEX

Explanations

terms related to legal or formal documentation and communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

sor

-0.14

âĢ¦

-0.13

âĢ¦↵

-0.13

cape

-0.13

—"

-0.13

iter

-0.13

—

-0.12

ÂĿ

-0.12

Sor

-0.12

od

-0.12

POSITIVE LOGITS

etto

0.15

eten

0.15

.fromFunction

0.14

optera

0.14

abbix

0.14

ursal

0.13

bjerg

0.13

upos

0.13

olib

0.13

onse

0.13

Activations Density 0.077%

terms related to legal or formal documentation and communication

No Comments

No Known Activations