INDEX

Explanations

terms related to scientific research and medical studies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Ø¯Ø§ÙĨÙĦÙĪØ¯

-0.14

ctxt

-0.14

');?>↵

-0.14

apo

-0.13

riv

-0.13

ÙİØ¯

-0.13

GLOBALS

-0.13

iveau

-0.13

 Individuals

-0.13

Ãºc

-0.13

POSITIVE LOGITS

Ø´ÙĨ

0.15

ÙĦØ§Ùħ

0.15

vanced

0.15

adget

0.14

agna

0.14

pek

0.14

argout

0.14

ìĬ¨

0.14

ogui

0.13

ç½²

0.13

Activations Density 0.228%

terms related to scientific research and medical studies

No Comments

No Known Activations