INDEX

Explanations

timestamps and time-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

entine

-0.16

 reserve

-0.16

coli

-0.16

atti

-0.15

 Reserve

-0.14

mour

-0.14

atan

-0.14

Enumerator

-0.14

 Jahres

-0.13

cano

-0.13

POSITIVE LOGITS

PDT

0.23

EST

0.22

 ÛĮÙĪØªÛĮ

0.22

EDT

0.22

MST

0.22

EST

0.20

edt

0.20

 cest

0.19

CST

0.19

YST

0.18

Activations Density 0.017%

timestamps and time-related information

No Comments

No Known Activations