INDEX

Explanations

specific programming and database-related terms and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

antal

-0.17

 BitConverter

-0.16

thon

-0.14

Ð¾ÑıÑĤ

-0.14

imuth

-0.14

orney

-0.14

 Readonly

-0.14

 intval

-0.13

omba

-0.13

zee

-0.13

POSITIVE LOGITS

 string

0.80

 String

0.76

-string

0.66

string

0.66

 strings

0.65

String

0.62

.string

0.60

åŃĹç¬¦ä¸²

0.59

 STRING

0.58

_string

0.58

Activations Density 0.150%

specific programming and database-related terms and constructs

No Comments

No Known Activations