INDEX

Explanations

numerical data, especially related to research studies or scientific measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

annon

-0.20

Bes

-0.15

odd

-0.15

aux

-0.15

empo

-0.14

rus

-0.14

ahren

-0.14

Bes

-0.14

orr

-0.14

enson

-0.14

POSITIVE LOGITS

burgh

0.17

HCI

0.15

 offsetof

0.14

(&(

0.14

EFA

0.14

EIF

0.14

ì°¸

0.14

istr

0.14

hire

0.13

è®

0.13

Activations Density 0.025%

numerical data, especially related to research studies or scientific measurements

No Comments

No Known Activations