INDEX

Explanations

terms related to architectural concepts and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

celik

-0.19

|array

-0.18

pled

-0.18

 NOTHING

-0.18

.sharedInstance

-0.16

Ð²ÐµÐ½

-0.16

lak

-0.16

ãĥĥ

-0.15

egment

-0.15

nothing

-0.15

POSITIVE LOGITS

 even

0.23

 Even

0.20

Even

0.20

even

0.19

 EVEN

0.18

 actually

0.16

ies

0.16

 BaseType

0.16

 sogar

0.15

 Ð´Ð°Ð¶Ðµ

0.15

Activations Density 0.014%

terms related to architectural concepts and their significance

No Comments

No Known Activations