INDEX

Explanations

explicit language and profanity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.14

las

-0.14

 Kare

-0.13

iev

-0.13

å±ķ

-0.13

æī¿

-0.13

dest

-0.13

 Bakan

-0.13

ector

-0.13

 Hillary

-0.13

POSITIVE LOGITS

èĦĤ

0.16

illy

0.15

ä¼¦

0.15

adge

0.15

iffe

0.15

à¸Ĺà¸£à¸ĩ

0.14

wik

0.14

 pokoj

0.14

ignon

0.14

illon

0.14

Activations Density 0.028%

explicit language and profanity

No Comments

No Known Activations