INDEX

Explanations

references to pop culture and entertainment news outlets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Īëĭ¤

-0.15

istik

-0.14

ibold

-0.14

plusplus

-0.14

ÄįnÃ¡

-0.14

 ÄĮeskÃ©

-0.14

esel

-0.14

ë¹Į

-0.14

ulp

-0.13

 Wert

-0.13

POSITIVE LOGITS

 docs

0.17

TMZ

0.17

--

0.16

imonial

0.15

ãĥ³ãĥĦ

0.15

tor

0.15

agli

0.15

åĪļæīį

0.14

czy

0.14

chn

0.14

Activations Density 0.002%

references to pop culture and entertainment news outlets

No Comments

No Known Activations