INDEX

Explanations

terms that indicate the provision of information, resources, or guidance

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

ãĥ«ãĥī

-0.16

orte

-0.14

cores

-0.14

oster

-0.14

ÐµÐ½ÑĮ

-0.14

å¤§ãģį

-0.14

ÑĮÑı

-0.14

ripper

-0.13

ulfilled

-0.13

znik

-0.13

POSITIVE LOGITS

 insight

0.35

 insights

0.33

 concrete

0.27

 guidance

0.27

 practical

0.27

ins

0.23

Ins

0.22

 direction

0.21

Concrete

0.21

 tools

0.21

Activations Density 0.137%

terms that indicate the provision of information, resources, or guidance

No Comments

No Known Activations