INDEX

Explanations

names and terms associated with individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

aland

-0.18

angelo

-0.17

leta

-0.17

uffer

-0.17

iel

-0.16

ussen

-0.16

æĳĺ

-0.15

elles

-0.15

 Lion

-0.15

åĨĴ

-0.15

POSITIVE LOGITS

-ing

0.17

illac

0.15

upe

0.15

_Utils

0.15

thouse

0.15

 Wade

0.15

linky

0.15

istrovstvÃŃ

0.15

BindingUtil

0.15

(~(

0.14

Activations Density 0.015%

names and terms associated with individuals or organizations

No Comments

No Known Activations