INDEX

Explanations

references to change and transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

prung

-0.15

 Dise

-0.15

etur

-0.15

marine

-0.15

jde

-0.14

Î¸Î¼

-0.14

 Thornton

-0.14

©

-0.14

iguiente

-0.14

anÃ¡

-0.14

POSITIVE LOGITS

inas

0.18

ÎºÎµÎ¹

0.15

riad

0.14

aim

0.14

itrust

0.14

 uncon

0.13

rup

0.13

SSF

0.13

iant

0.13

 Asheville

0.13

Activations Density 0.011%

references to change and transformation

No Comments

No Known Activations