INDEX

Explanations

specific programming structures and terminology likely related to software or database fields 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oda

-0.15

zes

-0.15

yssey

-0.14

ãĤĥ

-0.14

èĨ

-0.14

Ø§ÙĩØ§

-0.14

mÃ¡n

-0.14

immel

-0.14

Ð¾ÑĤÑĮ

-0.14

ickey

-0.13

POSITIVE LOGITS

iny

0.17

inya

0.15

azy

0.15

 Schultz

0.14

aryana

0.14

INY

0.14

eza

0.14

Äįet

0.14

ä¾Ľ

0.14

à¤Łà¤ķ

0.14

Activations Density 0.325%

specific programming structures and terminology likely related to software or database fields and operations

No Comments

No Known Activations