INDEX

Explanations

punctuation marks, particularly exclamation points and question marks

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

ãĥ¼ãĥľ

-0.14

à¥įà¤¸à¤°

-0.14

utow

-0.14

bab

-0.14

antee

-0.14

 Diamonds

-0.14

aÄĩ

-0.14

 Hart

-0.14

ajo

-0.13

amik

-0.13

POSITIVE LOGITS

geist

0.15

KK

0.15

cope

0.14

_cre

0.14

UTERS

0.14

han

0.14

ocht

0.14

opak

0.14

 visite

0.14

orz

0.13

Activations Density 0.036%

punctuation marks, particularly exclamation points and question marks

No Comments

No Known Activations