INDEX

Explanations

numerical values and references related to years and dates

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

omp

-0.15

kat

-0.15

estr

-0.14

usch

-0.14

ure

-0.14

ãĥ¼ãĥ«ãĥī

-0.14

tes

-0.14

emm

-0.14

 Pier

-0.14

ounce

-0.14

POSITIVE LOGITS

 Skyl

0.16

Mate

0.16

åģ¥

0.15

Ãłi

0.15

sek

0.15

YSTEM

0.15

ackage

0.14

ilere

0.14

osph

0.13

osaur

0.13

Activations Density 0.022%

numerical values and references related to years and dates

No Comments

No Known Activations