INDEX

Explanations

programming-related terms, particularly those associated with functions and callbacks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ezi

-0.16

strap

-0.15

ç«ĭãģ¦

-0.15

RAINT

-0.14

jack

-0.14

Von

-0.14

von

-0.14

Ð»Ð¸Ð½Ð¸

-0.13

Muk

-0.13

ease

-0.13

POSITIVE LOGITS

ipel

0.17

usercontent

0.15

IAS

0.15

ResponseStatus

0.15

iggs

0.15

herits

0.14

riday

0.14

QualifiedName

0.14

pent

0.13

Activations Density 0.133%

programming-related terms, particularly those associated with functions and callbacks

No Comments

No Known Activations