INDEX

Explanations

keywords related to layout or formatting in programming or design contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

utsch

-0.16

emale

-0.15

adel

-0.15

lients

-0.15

Ð²Ð¾Ð»Ñı

-0.14

zig

-0.14

zv

-0.14

meni

-0.14

 Äĳá»Ļc

-0.14

QL

-0.13

POSITIVE LOGITS

0.17

agen

0.17

aco

0.16

ãĥ¼ãĥĭ

0.15

 bump

0.15

otts

0.15

aped

0.14

 tslint

0.14

cal

0.14

tr

0.14

Activations Density 0.000%

keywords related to layout or formatting in programming or design contexts

No Comments

No Known Activations