INDEX

Explanations

programming-related syntax elements 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

 sing

-0.16

ingham

-0.16

enko

-0.15

 Circular

-0.15

egree

-0.14

 circular

-0.14

Len

-0.14

æļ

-0.14

minster

-0.14

-desktop

-0.14

POSITIVE LOGITS

Fold

0.20

hl

0.20

(Code

0.20

 highlight

0.20

 Fold

0.20

 fold

0.20

fold

0.19

LineNumber

0.19

 folds

0.19

 Code

0.17

Activations Density 0.042%

programming-related syntax elements and structures

No Comments

No Known Activations