INDEX

Explanations

specific dates and numerical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

plat

-0.16

rosis

-0.15

Uns

-0.15

UDO

-0.15

 Donald

-0.14

letal

-0.14

Donald

-0.14

ÏĦÎ¹ÎºÎ±

-0.14

ington

-0.14

POSITIVE LOGITS

 vaccination

0.30

 Vacc

0.27

 vaccinations

0.27

 vaccinated

0.27

 vacc

0.26

 vaccines

0.25

 vaccine

0.24

 shots

0.23

 Vaccine

0.22

 immun

0.21

Activations Density 0.034%

specific dates and numerical references

No Comments

No Known Activations