INDEX

Explanations

abbreviations and references related to scientific literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

oug

-0.16

á»ķ

-0.16

iks

-0.14

ibble

-0.14

 Mesa

-0.14

aign

-0.14

-Ta

-0.13

jedn

-0.13

 agreg

-0.13

 currency

-0.13

POSITIVE LOGITS

et

0.17

()."

0.16

ettes

0.16

.vs

0.15

ktor

0.15

isas

0.15

 Nicholson

0.15

éĭ

0.15

.bunifuFlatButton

0.15

luv

0.15

Activations Density 0.098%

abbreviations and references related to scientific literature

No Comments

No Known Activations