INDEX

Explanations

words related to wagons and personal names or locations associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

amped

-0.15

 Barnett

-0.14

checksum

-0.14

ãĥ«ãĥī

-0.14

ments

-0.14

lectual

-0.14

ÎºÏĮ

-0.14

anlar

-0.14

uddle

-0.14

bane

-0.14

POSITIVE LOGITS

ington

0.18

 trick

0.17

echa

0.17

sak

0.15

 Dynam

0.15

hol

0.15

habi

0.15

Ø§Ø±Ø´

0.15

Kre

0.14

eri

0.14

Activations Density 0.020%

words related to wagons and personal names or locations associated with them

No Comments

No Known Activations