INDEX

Explanations

programming constructs and function definitions 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

uen

-0.15

yny

-0.15

Bom

-0.15

omor

-0.15

rena

-0.15

ÑĢÐ¾Ñĩ

-0.15

_visitor

-0.14

ervo

-0.14

PHONE

-0.14

eki

-0.14

POSITIVE LOGITS

igits

0.15

abwe

0.15

COD

0.14

 digits

0.14

COD

0.14

[image

0.14

antor

0.13

ÑĤÐ°Ð¿

0.13

reau

0.13

Matchers

0.13

Activations Density 0.071%

programming constructs and function definitions in code

No Comments

No Known Activations