INDEX

Explanations

programming-related terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ooter

-0.17

boot

-0.16

	endif

-0.16

erin

-0.16

ãĥŃãĥ¼

-0.15

elly

-0.14

anje

-0.14

ore

-0.14

.toUpperCase

-0.14

 ÎłÎ¬

-0.14

POSITIVE LOGITS

nil

0.27

 rescue

0.26

 unless

0.26

Nil

0.20

unless

0.20

CGI

0.19

{|

0.19

 Rescue

0.19

nit

0.19

 respond

0.19

Activations Density 0.016%

programming-related terms and structures

No Comments

No Known Activations