INDEX

Explanations

programming-related functions and variables

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

Äįek

-0.16

-0.15

lander

-0.14

 Corey

-0.14

omen

-0.14

estre

-0.14

 Evet

-0.14

itude

-0.14

porte

-0.14

POSITIVE LOGITS

Kub

0.17

 ÐļÐ¾Ð»Ð¸

0.15

 Haut

0.15

omik

0.14

opak

0.14

kop

0.14

ubat

0.13

éĽĦ

0.13

åĪĹ

0.13

zk

0.13

Activations Density 0.101%

programming-related functions and variables

No Comments

No Known Activations