INDEX

Explanations

words related to entertainment or media content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ekler

-0.16

wers

-0.15

Ã©ri

-0.15

ÐµÐ»Ð¸Ñĩ

-0.14

dna

-0.14

Gap

-0.14

edii

-0.14

lish

-0.14

 INITIAL

-0.14

 Emin

-0.14

POSITIVE LOGITS

 sole

0.16

du

0.15

Leh

0.14

Stamped

0.14

0.13

ijd

0.13

 carte

0.13

fried

0.13

 dispos

0.13

/packages

0.13

Activations Density 0.000%

words related to entertainment or media content

No Comments

No Known Activations