INDEX

Explanations

actions and processes related to learning and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 whom

-0.15

ogan

-0.15

 alike

-0.14

.metro

-0.14

ÂĲ

-0.13

 jsonObj

-0.13

ul

-0.13

nger

-0.13

lea

-0.13

 Ð·Ð°Ðº

-0.13

POSITIVE LOGITS

olley

0.19

/Dk

0.17

.opendaylight

0.15

peare

0.15

ewire

0.15

aptors

0.15

tplib

0.15

roperty

0.15

ONES

0.15

omanip

0.14

Activations Density 0.107%

actions and processes related to learning and understanding

No Comments

No Known Activations