INDEX

Explanations

structured data or attributes related to programming and application interfaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

velt

-0.16

ÅĻ

-0.16

eyn

-0.15

ucken

-0.15

ÅĻen

-0.15

anmar

-0.15

isoft

-0.14

 Ekon

-0.14

urent

-0.14

rij

-0.14

POSITIVE LOGITS

éħĴ

0.16

ëł´

0.15

Joe

0.15

xFFFFFF

0.15

ãĤ¤ãĥ«

0.14

Joe

0.14

rypto

0.14

aka

0.14

enda

0.14

 para

0.14

Activations Density 0.307%

structured data or attributes related to programming and application interfaces

No Comments

No Known Activations