INDEX

Explanations

corporate entities and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

pective

-0.17

ilos

-0.17

ovan

-0.16

 meille

-0.14

 Lucia

-0.14

ATAR

-0.14

Luc

-0.14

èĦ

-0.13

ziej

-0.13

xfe

-0.13

POSITIVE LOGITS

åĳ³

0.15

bow

0.14

 flag

0.13

viso

0.13

 Wise

0.13

 Pruitt

0.13

unn

0.13

TL

0.13

iten

0.13

ãĥĥ

0.13

Activations Density 0.024%

corporate entities and their affiliations

No Comments

No Known Activations