INDEX

Explanations

references to the concept of origin

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ington

-0.18

LV

-0.14

irt

-0.14

lem

-0.13

ow

-0.13

ijing

-0.13

erman

-0.13

ÅĻ

-0.13

aise

-0.13

umper

-0.13

POSITIVE LOGITS

/source

0.18

entially

0.16

ator

0.16

ONGL

0.16

arily

0.15

uyla

0.15

prÃ¼

0.15

Matchers

0.15

dden

0.14

usb

0.14

Activations Density 0.028%

references to the concept of origin

No Comments

No Known Activations