INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

cplusplus

-0.18

 Fauc

-0.16

/sdk

-0.16

trap

-0.15

ä»

-0.15

omer

-0.15

 fauc

-0.15

OLUM

-0.14

 Mission

-0.14

ÑĢÐ¾Ð²Ð°

-0.14

POSITIVE LOGITS

 dataType

0.20

$.

0.20

 JsonRequestBehavior

0.19

.ajax

0.19

 textStatus

0.18

jq

0.18

.setRequestHeader

0.17

æ¨

0.17

.responseText

0.17

 Jackson

0.16

Activations Density 0.158%

programming-related terms and functions

No Comments

No Known Activations