INDEX

Explanations

references to analysis, resources, and educational content related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 à¤ªà¤¡

-0.14

 Crud

-0.14

oplevel

-0.14

Å¥

-0.14

_HI

-0.14

verity

-0.13

_ENSURE

-0.13

 Hood

-0.13

allo

-0.13

marvin

-0.13

POSITIVE LOGITS

 links

0.31

 Links

0.24

links

0.23

 tips

0.22

 list

0.22

 lists

0.22

 information

0.21

 details

0.21

-links

0.20

Links

0.19

Activations Density 0.329%

references to analysis, resources, and educational content related to various topics

No Comments

No Known Activations