INDEX

Explanations

names of people and places in the context of historical or cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Å¾ÃŃ

-0.18

buz

-0.15

nid

-0.15

abi

-0.15

orrow

-0.14

iceps

-0.14

uckle

-0.14

bios

-0.13

cep

-0.13

à¸ªà¸ģ

-0.13

POSITIVE LOGITS

 Medieval

0.22

 medieval

0.18

 Corpus

0.17

nun

0.16

 Monument

0.15

num

0.15

æł¡

0.15

ajor

0.15

Transmission

0.15

 antiqu

0.15

Activations Density 0.222%

names of people and places in the context of historical or cultural references

No Comments

No Known Activations