INDEX

Explanations

technical terms and parameters related to programming and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

aille

-0.17

)did

-0.17

afa

-0.16

/Foundation

-0.15

entials

-0.15

 endwhile

-0.15

alon

-0.15

-0.14

 createState

-0.14

POSITIVE LOGITS

 should

0.15

agas

0.15

 Silver

0.15

 aged

0.15

 extra

0.15

 Angelo

0.15

Silver

0.14

hints

0.14

 when

0.14

Fan

0.14

Activations Density 0.042%

technical terms and parameters related to programming and libraries

No Comments

No Known Activations