INDEX

Explanations

programming terminology and data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ymm

-0.16

iban

-0.15

ÙĪÙħÛĮ

-0.15

oltip

-0.15

peria

-0.15

leck

-0.15

ÑĩÐ¸ÑĤ

-0.14

kus

-0.14

Encoded

-0.14

Ð¾Ñĥ

-0.14

POSITIVE LOGITS

.gdx

0.15

fox

0.14

Ð°Ð»Ñİ

0.14

_connector

0.14

Ã¼ndeki

0.14

ichte

0.14

ittings

0.14

 Fortune

0.14

asan

0.13

ours

0.13

Activations Density 0.013%

programming terminology and data types

No Comments

No Known Activations