INDEX

Explanations

references to a specific brand or product name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

acz

-0.16

aroo

-0.15

 Verm

-0.15

ksam

-0.15

-0.14

 Cousins

-0.14

ander

-0.14

ULAR

-0.14

alet

-0.14

POSITIVE LOGITS

igious

0.25

byterian

0.17

ige

0.17

apl

0.16

wick

0.16

ASI

0.15

wich

0.15

º

0.15

idge

0.14

Activations Density 0.004%

references to a specific brand or product name

No Comments

No Known Activations