INDEX

Explanations

references to software libraries and their versions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

tere

-0.19

 Chamber

-0.16

cone

-0.16

enthal

-0.15

.djang

-0.15

 Consort

-0.14

æ½®

-0.14

 Consortium

-0.14

 Soon

-0.13

POSITIVE LOGITS

jar

0.25

.jar

0.24

Jar

0.23

jar

0.21

 jars

0.20

 commons

0.19

Jar

0.16

commons

0.16

-parent

0.16

hq

0.16

Activations Density 0.036%

references to software libraries and their versions

No Comments

No Known Activations