INDEX

Explanations

programming concepts related to setting and defining properties in objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

lec

-0.16

åħ¬éĸĭ

-0.15

 Walker

-0.15

krit

-0.14

 Humb

-0.14

chem

-0.14

enberg

-0.14

ensi

-0.14

eldorf

-0.14

ERM

-0.13

POSITIVE LOGITS

0.18

eni

0.17

0.14

Tu

0.14

Isl

0.14

bserv

0.14

.ActionListener

0.14

vre

0.14

anik

0.13

Activations Density 0.216%

programming concepts related to setting and defining properties in objects

No Comments

No Known Activations