INDEX

Explanations

references to different versions of a product or work

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

oÅĪ

-0.17

iet

-0.15

ride

-0.14

eway

-0.14

iyan

-0.14

 popcorn

-0.14

actionDate

-0.14

eron

-0.14

ert

-0.14

unch

-0.13

POSITIVE LOGITS

TY

0.18

nage

0.16

pNet

0.16

imli

0.16

dec

0.15

 versions

0.15

multiline

0.14

è¨Ī

0.14

TED

0.14

aleigh

0.14

Activations Density 0.041%

references to different versions of a product or work

No Comments

No Known Activations