INDEX

Explanations

mentions of patents and patent numbers

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

anders

-0.17

Ã§e

-0.15

urst

-0.14

Ã§ek

-0.14

)frame

-0.14

etz

-0.13

unbind

-0.13

ussen

-0.13

POSITIVE LOGITS

rive

0.17

«ĺ

0.16

lotte

0.16

áºŃu

0.15

zn

0.15

strt

0.15

 nale

0.14

plib

0.14

letes

0.14

STRU

0.14

Activations Density 0.024%

mentions of patents and patent numbers

No Comments

No Known Activations