INDEX

Explanations

programming-related terms and constructs, particularly those associated with query parameters and session management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

eah

-0.18

-0.14

hammer

-0.14

 Ventura

-0.14

acking

-0.14

andom

-0.14

ierre

-0.14

ÅĻik

-0.14

shire

-0.14

shima

-0.13

POSITIVE LOGITS

HasBeenSet

0.18

urat

0.16

lund

0.15

adil

0.14

ScrollIndicator

0.13

oras

0.13

Constructed

0.13

emplace

0.13

 PropertyChangedEventArgs

0.13

acias

0.13

Activations Density 0.003%

programming-related terms and constructs, particularly those associated with query parameters and session management

No Comments

No Known Activations