INDEX

Explanations

programming terminology and code structure related to querying parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Goldman

-0.16

rement

-0.15

ìłĪ

-0.14

uien

-0.14

stro

-0.14

IES

-0.14

HEX

-0.14

bral

-0.14

åĬŁ

-0.13

POSITIVE LOGITS

plen

0.18

Ð»Ð¸Ðº

0.15

'gc

0.15

 Morm

0.15

ÑİÐº

0.14

erah

0.14

 Protector

0.14

ignty

0.14

<location

0.14

redirectTo

0.13

Activations Density 0.385%

programming terminology and code structure related to querying parameters

No Comments

No Known Activations