INDEX

Explanations

terms related to resource consumption, particularly energy or material use

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

inha

-0.16

aria

-0.15

 Zucker

-0.14

ules

-0.14

indow

-0.14

iesen

-0.14

UpInside

-0.14

Î³Îµ

-0.14

xies

-0.14

 repr

-0.14

POSITIVE LOGITS

.nano

0.16

><?

0.15

ning

0.15

otch

0.15

Gaz

0.15

enza

0.15

webs

0.14

hel

0.14

cala

0.14

mtx

0.14

Activations Density 0.004%

terms related to resource consumption, particularly energy or material use

No Comments

No Known Activations