INDEX

Explanations

references related to programming concepts and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

adder

-0.15

fuscated

-0.15

enna

-0.15

ohn

-0.14

Ð¿ÑĢÐ¸

-0.14

Ð°Ð½ÑĮ

-0.14

ffee

-0.13

usto

-0.13

sep

-0.13

ustin

-0.13

POSITIVE LOGITS

å¥Ķ

0.15

Dud

0.14

0.13

inski

0.13

_UNIX

0.13

_TA

0.13

ãĥĥ

0.13

_tail

0.13

|=

0.13

 suddenly

0.13

Activations Density 0.081%

references related to programming concepts and operations

No Comments

No Known Activations