INDEX

Explanations

programming-related terms and operators used 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

OffsetTable

-0.15

represent

-0.14

ãģªãģĮ

-0.14

 representa

-0.14

appen

-0.13

lasses

-0.13

 Garland

-0.13

bert

-0.13

vron

-0.13

ibilit

-0.13

POSITIVE LOGITS

 Greater

0.23

lt

0.23

 operator

0.23

gt

0.22

_operator

0.22

gt

0.22

Operator

0.22

 operators

0.22

 Operator

0.21

lt

0.21

Activations Density 0.089%

programming-related terms and operators used in code

No Comments

No Known Activations