INDEX

Explanations

technical terms and functions related to database queries and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

landa

-0.15

ypes

-0.15

zych

-0.15

batim

-0.14

yor

-0.14

ombine

-0.14

aunch

-0.14

estre

-0.13

 quotes

-0.13

ÄĽt

-0.13

POSITIVE LOGITS

lag

0.26

 partition

0.24

-window

0.24

Lag

0.23

lag

0.23

 Partition

0.23

 Window

0.23

 window

0.23

 WINDOW

0.23

partition

0.22

Activations Density 0.026%

technical terms and functions related to database queries and operations

No Comments

No Known Activations