INDEX

Explanations

announcements regarding changes or transitions in Google services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 reopened

-0.18

 reopening

-0.17

_Delay

-0.16

 redis

-0.15

 reopen

-0.15

enan

-0.15

arra

-0.15

 refreshed

-0.15

 rebound

-0.14

 resetting

-0.14

POSITIVE LOGITS

 phase

0.40

 phased

0.39

ph

0.35

phase

0.35

 shut

0.33

 winding

0.32

 decom

0.32

 discontin

0.31

 Phase

0.31

 phases

0.31

Activations Density 0.265%

announcements regarding changes or transitions in Google services

No Comments

No Known Activations