INDEX

Explanations

elements related to programming options and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

lds

-0.14

Intersection

-0.14

alta

-0.13

CHK

-0.13

eph

-0.13

 Stevenson

-0.13

 strtok

-0.13

 vict

-0.13

mp

-0.13

 imper

-0.13

POSITIVE LOGITS

 indent

0.41

 tabs

0.38

tab

0.38

 indentation

0.37

Tab

0.37

TAB

0.37

Indent

0.36

Ind

0.36

indent

0.35

Tab

0.35

Activations Density 0.053%

elements related to programming options and settings

No Comments

No Known Activations