INDEX

Explanations

features related to technology and gadget specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eyin

-0.16

zet

-0.16

akter

-0.15

å¡ļ

-0.15

vio

-0.15

ApplicationBuilder

-0.14

ious

-0.14

otch

-0.14

POSITIVE LOGITS

Dol

0.17

mov

0.16

 recognition

0.15

IMENT

0.15

Rog

0.13

 Consortium

0.13

Å¡lo

0.13

chner

0.13

Yes

0.13

illiseconds

0.13

Activations Density 0.012%

features related to technology and gadget specifications

No Comments

No Known Activations