INDEX

Explanations

terms related to biological experimentation and research outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Pony

-0.16

æī§

-0.16

 nett

-0.15

å¤®

-0.15

Elk

-0.15

 ÑĢÑĥÐºÐ°Ð¼Ð¸

-0.15

bart

-0.15

ihat

-0.15

VRT

-0.15

phas

-0.15

POSITIVE LOGITS

 mice

0.39

 rats

0.34

 animals

0.31

 mouse

0.31

 rodents

0.29

 Animals

0.29

rat

0.28

animals

0.26

rats

0.26

 Mouse

0.24

Activations Density 0.080%

terms related to biological experimentation and research outcomes

No Comments

No Known Activations