INDEX

Explanations

references to individuals with the suffix "Jr." indicating they are junior versions of their namesakes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

amarin

-0.16

cat

-0.14

cis

-0.14

 relative

-0.14

ÏĮÎ³

-0.14

Acceleration

-0.13

 Kami

-0.13

PEAR

-0.13

ier

-0.13

 laisse

-0.13

POSITIVE LOGITS

.scalablytyped

0.17

duit

0.15

ihan

0.15

INET

0.15

registry

0.15

-Semit

0.15

own

0.15

.Actor

0.15

ekli

0.14

ohn

0.14

Activations Density 0.005%

references to individuals with the suffix "Jr." indicating they are junior versions of their namesakes

No Comments

No Known Activations