INDEX

Explanations

terms and elements related to database operations and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

irim

-0.16

éĽħ

-0.15

rug

-0.15

ANGED

-0.14

elden

-0.14

ington

-0.13

 stages

-0.13

 Collapse

-0.13

 rugs

-0.13

_TRANSFORM

-0.13

POSITIVE LOGITS

oler

0.18

AndView

0.17

iero

0.15

dsl

0.15

oled

0.15

Kit

0.15

ourcem

0.14

yped

0.14

olem

0.14

ournÃ©e

0.14

Activations Density 0.168%

terms and elements related to database operations and structures

No Comments

No Known Activations