INDEX

Explanations

references to dictionary and database operations in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ì²´

-0.15

elmet

-0.15

emez

-0.15

 ç§ĭ

-0.14

.spin

-0.14

_mk

-0.14

fak

-0.14

GRADE

-0.14

cak

-0.14

ige

-0.14

POSITIVE LOGITS

opis

0.15

Í

0.15

Arb

0.14

ģ

0.13

ÐµÑģÐ°

0.13

etto

0.13

emento

0.13

Dos

0.13

orum

0.12

eer

0.12

Activations Density 0.078%

references to dictionary and database operations in programming contexts

No Comments

No Known Activations