INDEX

Explanations

numerical data and statistics related to measurements or rankings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raki

-0.15

 porte

-0.15

OptionsMenu

-0.15

issen

-0.14

xn

-0.14

eration

-0.14

 tavs

-0.14

 ÄĮer

-0.14

Ð¾ÑģÑĤÐ°Ð²

-0.14

 cancelButtonTitle

-0.14

POSITIVE LOGITS

dic

0.17

dic

0.15

 diary

0.15

ango

0.14

heartbeat

0.14

ramework

0.14

isa

0.14

obook

0.14

uka

0.14

afa

0.13

Activations Density 0.009%

numerical data and statistics related to measurements or rankings

No Comments

No Known Activations