INDEX

Explanations

prepositions and phrases that indicate causality or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 itself

-0.15

aid

-0.14

ones

-0.14

Fle

-0.13

variants

-0.13

 correspondent

-0.13

uct

-0.13

ali

-0.13

ingen

-0.13

POSITIVE LOGITS

oret

0.15

ough

0.15

elho

0.14

ãĥ¼ãĥľ

0.14

.portal

0.14

PackageName

0.14

ÎºÎ®

0.14

Î¿ÏħÎ½

0.14

.mime

0.14

 Redistributions

0.14

Activations Density 0.126%

prepositions and phrases that indicate causality or condition

No Comments

No Known Activations