INDEX

Explanations

programming code elements and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

enko

-0.15

 sing

-0.15

æļ

-0.15

Len

-0.15

 Freed

-0.14

uppercase

-0.14

enti

-0.14

 circular

-0.14

minster

-0.14

ucci

-0.14

POSITIVE LOGITS

 highlight

0.23

hl

0.23

 highlighting

0.20

Fold

0.20

(Code

0.19

hl

0.19

highlight

0.19

 Highlight

0.19

 Code

0.19

LineNumber

0.19

Activations Density 0.071%

programming code elements and structure

No Comments

No Known Activations