INDEX

Explanations

programming-related syntax and data types in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

.debugLine

-0.14

ograf

-0.14

azole

-0.14

clist

-0.13

ENO

-0.13

errer

-0.13

 Echo

-0.13

iras

-0.13

cid

-0.13

imo

-0.13

POSITIVE LOGITS

 aligned

0.25

 little

0.25

 alignment

0.25

 word

0.25

Aligned

0.24

aligned

0.23

 endian

0.23

 signed

0.23

 WORD

0.23

_aligned

0.23

Activations Density 0.020%

programming-related syntax and data types in code

No Comments

No Known Activations